Generated by All in One SEO Pro v5.0.0.1, this is an llms.txt file, used by LLMs to index the site. # LearnOpenCV Learn OpenCV, PyTorch, Keras, Tensorflow with code, & tutorials ## Sitemaps - [XML Sitemap](https://learnopencv.com/sitemap.xml): Contains all public & indexable URLs for this website. ## Posts - [Blogs](https://learnopencv.com/blogs/) - [The Ultimate Guide to Vector DB and RAG Pipeline](https://learnopencv.com/vector-db-and-rag-pipeline-for-document-rag/) - Processing long documents with VLMs poses a huge challenge. Document RAG pipeline - Vector DB and RAG address this by enabling semantic retrieval. - [Video Generation: Evolution from VDM to Veo2 and SORA](https://learnopencv.com/video-generation-models/) - A diffusion-based approach for high-quality, physics-consistent video generation, evolving from VDM to Veo 2 and SORA with open-source models like Hunyuan Video - [MiniCPM-o 4.5: A 9B Model That Can See, Hear, and Speak at the Same Time](https://learnopencv.com/minicpm-o-4-5-a-9b-model-that-can-see-hear-and-speak-at-the-same-time/) - MiniCPM-o 4.5 is a 9B open-source model that can see, hear, and speak simultaneously. We test its full-duplex Omni-Flow streaming on real-world videos. - [Video Stabilization Using Point Feature Matching in OpenCV](https://learnopencv.com/video-stabilization-using-point-feature-matching-in-opencv/) - In this post we will discuss how to implement Video Stabilization using Point Feature Matching in OpenCV using Python and C++. - [Understanding Lens Distortion](https://learnopencv.com/understanding-lens-distortion/) - Updated July 31, 2026: This is a conservative correction of the original article. Its correct narrative, worked examples, and media are retained; only identified mistakes, obsolete compatibility details, and missing validation guidance are corrected. In a previous post, we went over the geometry of image formation and learned how a point in 3D gets projected - [Super Resolution in OpenCV](https://learnopencv.com/super-resolution-in-opencv/) - Super resolution is the process of upscaling or improving the details of the image. This blog is a quick comparison of algorithms on Super Resolution in OpenCV. - [Snake Game with OpenCV Python](https://learnopencv.com/snake-game-with-opencv-python/) - In this post, we share a tutorial for creating the snake game using OpenCV GUI. - [Shape Matching using Hu Moments (C++/Python)](https://learnopencv.com/shape-matching-using-hu-moments-c-python/) - How to use Hu Moments for Shape Matching. The theory is explained and example OpenCV code is shared in C++ and Python. - [Rotation Matrix To Euler Angles](https://learnopencv.com/rotation-matrix-to-euler-angles/) - The post contains C++ and Python code for converting a rotation matrix to Euler angles and vice-versa. It is based on Matlab's rotm2euler. - [Read, Write and Display a video using OpenCV](https://learnopencv.com/read-write-and-display-a-video-using-opencv-cpp-python/) - A tutorial on how to read, write and display a video using OpenCV. OpenCV-Python and OpenCV-C++ Code is provided for practice and understanding. - [Read, Display and Write an Image using OpenCV](https://learnopencv.com/read-display-and-write-an-image-using-opencv/) - Learn how to Read, Display and Write an Image using OpenCV. We discuss OpenCV functions, their syntax and options. - [Otsu's Thresholding with OpenCV](https://learnopencv.com/otsu-thresholding-with-opencv/) - Updated July 31, 2026: The original tutorial, examples, media, narrative, and teaching order are preserved below. The labelled 2026 correction area adds only the verified API, compatibility, validation, and failure-handling changes needed for current OpenCV; where a historical snippet uses an obsolete API, the correction area is the runnable path. In this post, we will - [Optical Flow in OpenCV (C++/Python)](https://learnopencv.com/optical-flow-in-opencv/) - In this post, we will take a look at the theoretical aspects of Optical Flow algorithms and their practical usage with OpenCV. - [OpenCV QR Code Scanner ( C++ and Python )](https://learnopencv.com/opencv-qr-code-scanner-c-and-python/) - We will describe how to use the QR Code scanner in OpenCV. We will also compare it with ZBar library. The code is shared in C++ and Python - [Understanding Visual SLAM for Robotics Perception: Building Monocular SLAM from Scratch in Python OpenCV](https://learnopencv.com/monocular-slam-in-python/) - Understanding what is Monocular SLAM, how to implement it in Python OpenCV? Learning Epipolar Geometry, Localization,Mapping, Loop Closure and working of ORB-SLAM - [Image Resizing with OpenCV](https://learnopencv.com/image-resizing-with-opencv/) - Learn about image resizing with OpenCV along with different interpolation methods. Also, learn about the different functions and syntax used for resizing. - [Image Quality Assessment : BRISQUE](https://learnopencv.com/image-quality-assessment-brisque/) - A tutorial on Image Quality Assessment for No-Reference models, using BRISQUE quality metric. We are sharing code in C++ and Python. - [Feature Based Image Alignment using OpenCV (C++/Python)](https://learnopencv.com/image-alignment-feature-based-using-opencv-c-python/) - Tutorial on feature-based image alignment using OpenCV. Also learn keypoint detection/matching, Homography & image warping. C++/Python code is shared for study. - [Image Alignment (ECC) in OpenCV ( C++ / Python )](https://learnopencv.com/image-alignment-ecc-in-opencv-c-python/) - See example code for using OpenCV ECC image alignment on mis-aligned color channels of historic images. - [Find frame rate (frames per second-fps) in OpenCV (Python/C++)](https://learnopencv.com/how-to-find-frame-rate-or-frames-per-second-fps-in-opencv-python-cpp/) - Tutorial on how to find frame rate or frames per second (fps) in a video using OpenCV. Python and C++ code is provided for practice and study. - [Hough Transform with OpenCV (C++/Python)](https://learnopencv.com/hough-transform-with-opencv-c-python/) - How to use Hough transform to detect circles and lines - [Homography examples using OpenCV ( Python / C ++ )](https://learnopencv.com/homography-examples-using-opencv-python-c/) - Blog on Homography, explaining the concept and theory. We discuss Homography examples using OpenCV. Python and C++ code is provided for study and practice. - [Histogram of Oriented Gradients explained using OpenCV](https://learnopencv.com/histogram-of-oriented-gradients/) - Histogram of Oriented Gradients (HOG) is a feature descriptor, used for object detection. Read the blog to learn the theory behind it and how it works. - [Head Pose Estimation using OpenCV and Dlib](https://learnopencv.com/head-pose-estimation-using-opencv-and-dlib/) - This is a tutorial on head pose estimation using OpenCV ( C++ and Python ) and Dlib. We use solvePnP and solvePnPRansac for pose estimation. - [Find the Center of a Blob (Centroid) using OpenCV (C++/Python)](https://learnopencv.com/find-center-of-blob-centroid-using-opencv-cpp-python/) - In this tutorial, we will learn how to find the centroid of a blob using OpenCV (C++/Python). We will also learn about image moments. - [Filling holes in an image using OpenCV ( Python / C++ )](https://learnopencv.com/filling-holes-in-an-image-using-opencv-python-c/) - This tutorial describes a method for filling holes in a binary image in OpenCV ( C++ / Python ). The method is similar to imfill in MATLAB. - [Face Detection - Dlib, OpenCV, and Deep Learning ( C++ / Python )](https://learnopencv.com/face-detection-opencv-dlib-and-deep-learning-c-python/) - Empirical comparison of Face Detectors in OpenCV, Dlib face detection & Deep Learning. Face Detectors based on Haar Cascade, HoG, and Deep Learning in Dlib. - [Edge Detection Using OpenCV](https://learnopencv.com/edge-detection-using-opencv/) - Learn about edge detection using OpenCV. Explore the different edge detection techniques like Sobel and Canny in OpenCV. - [Stereo Camera Depth Estimation With OpenCV (Python/C++)](https://learnopencv.com/depth-perception-using-stereo-camera-python-c/) - Stereo Camera Depth Estimation with OpenCV- Disparity map for rectified stereo image pair, depth map from disparity map-Bonus code for obstacle avoidance system - [Delaunay Triangulation & Voronoi Diagram Using OpenCV ( C++ / Python )](https://learnopencv.com/delaunay-triangulation-and-voronoi-diagram-using-opencv-c-python/) - Build and test Delaunay triangulations and Voronoi diagrams with OpenCV 4.14 and 5 using modern Python, C++17, Subdiv2D, and headless validation. - [Deep Learning Based OCR Text Recognition Using Tesseract and OpenCV](https://learnopencv.com/deep-learning-based-text-recognition-ocr-using-tesseract-and-opencv/) - In this tutorial, we will learn deep learning based OCR and how to recognize text in images (OCR) using Tesseract's Deep Learning based LSTM engine and OpenCV. - [Deep Learning based Human Pose Estimation using OpenCV](https://learnopencv.com/deep-learning-based-human-pose-estimation-using-opencv-cpp-python/) - Deep Learning based Human Pose Estimation using OpenCV. Tutorial on OpenPose, DNN based pose estimation framework. Python/C++ code is shared for study/practice. - [Cropping an Image using OpenCV](https://learnopencv.com/cropping-an-image-using-opencv/) - Learn how cropping an image using OpenCV works. Also, learn how you can divide an image into smaller patches using cropping. - [ Image Colorization Using CNN With OpenCV](https://learnopencv.com/convolutional-neural-network-based-image-colorization-using-opencv/) - Image colorization using CNN-Deep Learning architecture for Colorizing a black & white image explained + CNN based Image Colorization with C++/Python code - [Convex Hull using OpenCV in Python and C++](https://learnopencv.com/convex-hull-using-opencv-in-python-and-c/) - Tutorial for finding the Convex Hull of a shape or a group of points. Code is shared in C++ and Python code implementation using OpenCV. - [Contour Detection using OpenCV (Python/C++)](https://learnopencv.com/contour-detection-using-opencv-python-c/) - Learn contour detection using OpenCV. Not only the theory, we will also cover a complete hands-on coding in Python/C++ for a first hand, practical experience. - [Color spaces in OpenCV (C++ / Python)](https://learnopencv.com/color-spaces-in-opencv-cpp-python/) - Conversion between RGB, HSV, LAB and YCrCb color spaces and how to choose among them using OpenCV ( python and C++ ) - [Camera Calibration using OpenCV](https://learnopencv.com/camera-calibration-using-opencv/) - A step by step tutorial for calibrating a camera using OpenCV with code shared in C++ and Python. You will also understand the significance of various steps. - [Blob Detection Using OpenCV ( Python, C++ )](https://learnopencv.com/blob-detection-using-opencv-python-c/) - This beginner tutorial explains simple blob detection using OpenCV. C++ and Python code is available for study and practice. - [Barcode and QR Code Scanner Using ZBar and OpenCV](https://learnopencv.com/barcode-and-qr-code-scanner-using-zbar-and-opencv/) - Learn how to add a barcode and QR code scanner to your OpenCV application using ZBar. Step by step instructions with C++ and Python (2 and 3) code. - [Average Face : OpenCV ( C++ / Python ) Tutorial](https://learnopencv.com/average-face-opencv-c-python-tutorial/) - An OpenCV ( C++ / Python ) tutorial for aligning and averaging faces. - [Augmented Reality using ArUco Markers in OpenCV (C++ / Python)](https://learnopencv.com/augmented-reality-using-aruco-markers-in-opencv-c-python/) - We show how to use ArUco markers in OpenCV for augmented reality applications. We provide code in both C++ and Python. - [Object Tracking using OpenCV (C++/Python)](https://learnopencv.com/object-tracking-using-opencv-cpp-python/) - Object tracking using OpenCV, theory and tutorial on usage of of 8 different trackers in OpenCV. Python and C++ code is included for practice. - [Object Detection with OpenCV 5 in C++: YOLO26 Pose and Segmentation](https://learnopencv.com/opencv-5-cpp-object-detection-yolo26/) - Run YOLO26 object detection, pose estimation, team splitting, and instance segmentation on CPU with OpenCV 5 in C++, ONNX, and reproducible code. - [Install OpenCV 5 on Linux](https://learnopencv.com/install-opencv-5-linux/) - Install OpenCV 5 on Linux with pip, C++ source, or CUDA. Includes Ubuntu 24.04 tests, distro routing, strict checks, and a verifier bundle. - [Decoding Virat Kohli's Flick Shot: AI-Based 3D Motion Reconstruction](https://learnopencv.com/decoding-virat-kohlis-flick-shot-ai-based-3d-motion-reconstruction/) - Reconstruct the 3D swing plane of Virat Kohli's flick shot from a single 2D video with off-the-shelf vision models. No sensors, no motion-capture rig. - [How to Run Object Detection with OpenCV 5](https://learnopencv.com/how-to-run-object-detection-with-opencv-5/) - Learn about the new OpenCV 5 and how to use its DNN engine to run object detection models on the CPU, using real 2026 World Cup football footage. - [Deep Learning Book Gift Recipients](https://learnopencv.com/deep-learning-book-gift-recipients/) - In late December 2016, I announced a small gift of 10 Deep Learning books to people interested in or working in AI. This is my way of paying back to the community which has been extremely generous with ideas and code. I asked people to send me an email letting me know their interest in - [Pix2Pix:Image-to-Image Translation in PyTorch & TensorFlow](https://learnopencv.com/paired-image-to-image-translation-pix2pix/) - In Paired Image-to-Image translation or Pix2Pix translation of image from one to another domain occurs by learning a mapping between the input and output images. - [World Cup 2026 Offside Technology: AI, Computer Vision, and the Connected Ball](https://learnopencv.com/world-cup-2026-offside-technology/) - Learn how World Cup 2026 offside technology works with multi-camera tracking, AI pose estimation, digital twins, VAR, and the connected Trionda ball. - [AI Aced JEE Advanced 2026. Can You Trust It to Teach You?](https://learnopencv.com/ai-aced-jee-advanced-2026-can-you-trust-it-to-teach-you/) - A look inside the multi-agent design that keeps an AI tutor grounded in its textbook and code-checks every answer before a student ever sees it. - [How Computer Vision Solved the Greatest Soccer Mystery of All Time](https://learnopencv.com/how-computer-vision-solved-the-greatest-soccer-mystery-of-all-times/) - How top English researchers proved that the controversial 1966 World Cup goal by Geoff Hurst at Wembley was in fact not a goal! - [How to Fine-Tune YOLO26 for Safety Gear and Sign Language Detection](https://learnopencv.com/how-to-fine-tune-yolo26-for-safety-gear-and-sign-language-detection/) - Learn how to fine-tune YOLO26 on your own data. We build a construction PPE safety detector and a sign-language reader using one simple workflow. - [How to Master Qwen3-VL Embedding and Reranker for Multimodal Search](https://learnopencv.com/how-to-master-qwen3-vl-embedding-and-reranker-for-multimodal-search/) - Master Qwen3-VL Embedding and Reranker for multimodal retrieval: text, image, video, mixed-modal queries, and a two-stage pipeline that boosts precision. - [How to Master YOLOE: Real-Time Open-Vocabulary Detection Made Easy](https://learnopencv.com/yoloe-tutorial-real-time-open-vocabulary-detection/) - Learn YOLOE for real-time open-vocabulary object detection and instance segmentation in Python with Ultralytics — text, visual, and prompt-free modes. - [How to Unlock 5 Vision Skills with the Moondream Cloud API](https://learnopencv.com/moondream-cloud-api-one-image-five-grounded-vision-skills/) - Learn the Moondream Cloud API by running all five vision skills, caption, query, detect, point, and segment, on a single image with code and real outputs. - [JEE Advanced 2026: We Tested AI on the Toughest Exam](https://learnopencv.com/jee-advanced-2026-we-tested-ai-on-the-toughest-exam/) - Three frontier AI models took JEE Advanced 2026, one of the world's toughest exams. All three outscored every human who sat the paper. Here's how. - [YOLO26 Keypoint Estimation: Real-Time Pose Estimation with Ultralytics](https://learnopencv.com/yolo26-pose-estimation-tutorial/) - Hands-on YOLO26 pose estimation tutorial: real-time keypoint detection in Python, RLE architecture, and COCO-17 benchmarks explained. - [RF-DETR Segmentation: Real-Time Detection & Instance Segmentation Guide](https://learnopencv.com/rf-detr-segmentation-real-time-detection-instance-segmentation-guide/) - Learn how to use RF-DETR-Seg with Python for image and video inference, understand the architecture behind it, and evaluate its performance on COCO benchmarks. - [YOLO26 Instance Segmentation: Pixel-Perfect AI at Real-Time Speed](https://learnopencv.com/yolo26-instance-segmentation-pixel-perfect-ai-at-real-time-speed/) - Build a complete pipeline for YOLO26 instance segmentation, from image and video inference to custom dataset training and edge deployment. - [Mastering Multi-Object Tracking with Roboflow Trackers & OpenCV](https://learnopencv.com/multi-object-tracking-with-roboflow-trackers-and-opencv/) - Implement multi-object tracking with Roboflow Trackers and OpenCV. Apply ByteTrack and SORT to detect, track, and draw trajectories in real-world videos. - [Breaking the Bottleneck: Achieving Native NMS-Free Inference with YOLO26](https://learnopencv.com/yolo26-nms-free-inference/) - YOLO26 introduces NMS-free inference. Discover how its One-to-One label assignment eliminates post-processing overhead for stable, real-time edge performance. - [Serving SGLang: Launch a Production-Style Server](https://learnopencv.com/sglang-a-production-server/) - SGLang is a high-performance runtime for structured LLM programs, enabling fast KV cache reuse, parallel execution, and efficient serving. - [Beyond Transformers: A Deep Dive into HOPE](https://learnopencv.com/hope-beyond-transformers/) - Discover the HOPE architecture, a revolutionary self-modifying AI system that solves catastrophic forgetting and scales to 10 million tokens. - [YOLOv26: An Object Detector Built for Real-Time Deployment](https://learnopencv.com/yolov26-real-time-deployment/) - YOLOv26 is an edge-first object detector designed for real-time deployment, featuring NMS-free inference, quantization stability, and predictable latency. - [Real-Time Face Blur and Pixelation with OpenCV YuNet](https://learnopencv.com/face-blur-pixelation-opencv-yunet/) - Learn how to build a real-time face blur and pixelation app with OpenCV and YuNet in Python and C++. Detect faces from a webcam and anonymize them live. - [Vision Banana: How Image Generators Are Becoming Powerful Vision Models](https://learnopencv.com/vision-banana-explained/) - Vision Banana turns Nano Banana Pro into a powerful vision model for segmentation, depth estimation, surface normals, image generation, and editing. - [FineTuning SAM2 for Leaf Disease Segmentation – Step-by-Step Tutorial](https://learnopencv.com/finetuning-sam2/) - Learn how to fine-tune Meta’s SAM2 on a custom leaf disease dataset. Detect crop diseases early with deep learning in this step-by-step tutorial. - [Integrating Gradio with OpenCV DNN](https://learnopencv.com/integrating-gradio-with-opencv-dnn/) - Learn how to build real-time web applications using Gradio with OpenCV DNN for object detection, offering efficient and interactive AI experiences. - [FineTuning RetinaNet for Wildlife Detection with PyTorch: A Step-by-Step Tutorial](https://learnopencv.com/finetuning-retinanet/) - Master the process of finetuning RetinaNet using PyTorch for wildlife animal detection. This step-by-step tutorial covers dataset preparation, model training. - [Deployment on Edge: LLM Serving on Jetson using vLLM](https://learnopencv.com/deployment-on-edge-vllm-on-jetson/) - An article for Deployment on Edge. Run LLMs on an 8 GB Jetson Orin Nano, covering setup, failures, and a practical comparison between vLLM and llama.cpp. - [Nested Learning: Is Deep Learning Architecture an Illusion?](https://learnopencv.com/nested-learning/) - Nested Learning is a new paradigm that explains modern AI through learning-within-learning driven by optimization, memory, and in-context learning. - [How to Build a GitHub Code-Analyser Agent for Developer Productivity](https://learnopencv.com/how-to-build-a-github-code-analyser-agent/) - Understanding large GitHub repositories can be time-consuming. Code-Analyser tackles this problem by using an agentic, approach to parse and analyze codebases. - [The Existential Problems in LLM Serving](https://learnopencv.com/the-existential-problems-in-llm-serving/) - Naive Transformers is good for lab experiments, but not for production. Check out what are the major problems associated with Autoregressive inference. In this post, we will cover how modern engines like vLLM, SGLang, and more solves problems in LLM serving. - [SAM-3: What’s New, How It Works, and Why It Matters](https://learnopencv.com/sam-3-whats-new/) - Yet another SOTA model from META, meet SAM-3. Learn about what's new and how to implement your own tracking pipeline using SAM-3. - [YOLOv6 Object Detection - Paper Explanation and Inference](https://learnopencv.com/yolov6-object-detection/) - YOLOv6 is the latest model in the YOLO family of object detectors, mainly aimed toward industrial applications while achieving state-of-the-art detection - [YOLOv6 Object Detection - Paper Explanation and Inference](https://learnopencv.com/yolov6-object-detection/) - YOLOv6 is the latest model in the YOLO family of object detectors, mainly aimed toward industrial applications while achieving state-of-the-art detection - [Introduction to Robotics: A Comprehensive Guide to Robotics for Beginners](https://learnopencv.com/a-comprehensive-guide-to-robotics/) - Introduction to Robotics:Discover why learning in 2024 is vital.Explore project workflow, perception, planning,control,Tesla Autopilot,tools,jobs, and research. - [Training 3D U-Net for Brain Tumor Segmentation Challenge - Medical Imaging](https://learnopencv.com/3d-u-net-brats/) - Training a 3D U-Net model for the BraTS challenge enhances brain tumor segmentation in 3D MRI scans, improving diagnostic precision in medical imaging. - [VideoRAG: Redefining Long-Context Video Comprehension](https://learnopencv.com/videorag-long-context-video-comprehension/) - Discover VideoRAG, a framework that fuses graph-based reasoning and multi-modal retrieval to enhance LLMs' ability to understand multi-hour videos efficiently. - [SAM 3D: Foundation Model for Single-Image 3D Reconstruction](https://learnopencv.com/sam-3d/) - SAM 3D is Meta’s groundbreaking foundation model for reconstructing full 3D shape, texture, and object layout from a single natural image. Learn how it works. - [Getting Started with VLM on Jetson Nano](https://learnopencv.com/vlm-on-jetson-nano/) - Learn how to setup a pipeline to run VLM on Jetson Nano using Huggingface Transformers. Run models like LiquidAI, Moondream2, FastVLM, and SmolVLM. - [VLM on Edge: Worth the Hype or Just a Novelty?](https://learnopencv.com/vlm-on-edge-devices/) - Testing Vision Language Models (VLM) on edge devices. Check how small VLMs perform on our custom Raspberry Pi Cluster and Jetson Nanos. - [Image-GS: Adaptive Image Reconstruction using 2D Gaussians](https://learnopencv.com/image-gs-image-reconstruction-using-2d-gaussians/) - Discover Image-GS, an image representation framework based on adaptive 2D Gaussians, outperforming neural and classical codecs in terms of real-time efficiency. - [Deploying ML on Arduino: From Blink to Think](https://learnopencv.com/deploying-ml-on-arduino/) - Deploying ML on Arduino Nano 33 BLE. Explore TinyML techniques, setup steps, and why older Arduinos still rival the new Arduino Uno Q. - [What Makes DeepSeek OCR So Powerful?](https://learnopencv.com/what-makes-deepseek-ocr-so-powerful/) - DeepSeek OCR Paper explanation and Testing with Transformers and vLLM framework. Analysing fail cases and building rag app using Context Optical Compression. - [vLLM: Deploying LLMs at Scale Like OpenAI](https://learnopencv.com/vllm-deploy-llms-at-scale-paged-attention/) - vLLM Paper Explained. Understand how pagedAttention, and continuous batching works along with other optimizations by vLLM over time. - [YOLOv8 Object Tracking and Counting with OpenCV](https://learnopencv.com/yolov8-object-tracking-and-counting-with-opencv/) - YOLOv8 object tracking and counting unveils new dimensions in real-time tacking; explore its mastery in our detailed guide, your key to mastering the tech. - [WeChat QR Code Scanner in OpenCV](https://learnopencv.com/wechat-qr-code-scanner-in-opencv/) - Learn how to use the WeChat QR code scanner in OpenCV using Python and C++. We will also quantitatively and qualitatively compare its performance with default QR code decoder. - [Introduction to OAK-D and DepthAI](https://learnopencv.com/introduction-to-opencv-ai-kit-and-depthai/) - This is an introductory post to OAK-D, OpenCV AI Kit with Depth. You will learn about the OAK D device and the DepthAI pipeline for using the stereo cameras. - [Stereo Vision and Depth Estimation using OpenCV AI Kit](https://learnopencv.com/stereo-vision-and-depth-estimation-using-opencv-ai-kit/) - This OAK series article discusses the geometry of stereo vision & the depth estimation pipeline. Learn to solve hurdles in depth estimation & its limitations. - [Chrome Dino Player Bot using OpenCV Feature Matching](https://learnopencv.com/how-to-build-chrome-dino-game-bot-using-opencv-feature-matching/) - Learn to create a game controller for Chrome Dino using OpenCv Feature Matching.The bot uses AutoPyGUI to simulate keypress and MSS library to capture screen. - [MediaPipe - The Ultimate Guide to Video Processing](https://learnopencv.com/introduction-to-mediapipe/) - MediaPipe Uncovered: Your ultimate guide & central hub for all things MediaPipe, links to related posts on its varied applications from basic to advanced levels - [Building Body Posture Detection System Using MediaPipe](https://learnopencv.com/building-a-body-posture-analysis-system-using-mediapipe/) - Body posture detection and analysis system using MediaPipe and OpenCV. Learn how to build a real time bad posture alert application. Mediapipe pose. - [Building Body Posture Detection System Using MediaPipe](https://learnopencv.com/building-a-body-posture-analysis-system-using-mediapipe/) - Body posture detection and analysis system using MediaPipe and OpenCV. Learn how to build a real time bad posture alert application. Mediapipe pose. - [Building Body Posture Detection System Using MediaPipe](https://learnopencv.com/building-a-body-posture-analysis-system-using-mediapipe/) - Body posture detection and analysis system using MediaPipe and OpenCV. Learn how to build a real time bad posture alert application. Mediapipe pose. - [Object Detection using YOLOv5 OpenCV DNN in C++ and Python](https://learnopencv.com/object-detection-using-yolov5-and-opencv-dnn-in-c-and-python/) - A comprehensive guide to Object Detection using YOLOv5 OpenCV DNN framework. Learn how to run YOLOv5 inference both in C++ and Python. OpenCV YOLOv5. - [Object Detection using YOLOv5 OpenCV DNN in C++ and Python](https://learnopencv.com/object-detection-using-yolov5-and-opencv-dnn-in-c-and-python/) - A comprehensive guide to Object Detection using YOLOv5 OpenCV DNN framework. Learn how to run YOLOv5 inference both in C++ and Python. OpenCV YOLOv5. - [Object Detection using YOLOv5 OpenCV DNN in C++ and Python](https://learnopencv.com/object-detection-using-yolov5-and-opencv-dnn-in-c-and-python/) - A comprehensive guide to Object Detection using YOLOv5 OpenCV DNN framework. Learn how to run YOLOv5 inference both in C++ and Python. OpenCV YOLOv5. - [Intersection over Union (IoU) in Object Detection & Segmentation](https://learnopencv.com/intersection-over-union-iou-in-object-detection-and-segmentation/) - Intersection Over Union (IoU) is a helper metric for evaluating object detection and segmentation model. Learn from the basics to implementing IoU from scratch. - [Mean Average Precision (mAP) in Object Detection](https://learnopencv.com/mean-average-precision-map-object-detection-model-evaluation-metric/) - Mean Average Precision (mAP) is a evaluation metric used for evaluating machine learning models. We have covered mAP object detection metric in detail COCO mAP - [What is EXIF Data in Images?](https://learnopencv.com/what-is-exif-data-in-images/) - [EXIF python explained] Find out what is EXIF and how EXIF data can be used in various applications. Using EXIF to visualize potholes of a city on google maps. - [What is EXIF Data in Images?](https://learnopencv.com/what-is-exif-data-in-images/) - [EXIF python explained] Find out what is EXIF and how EXIF data can be used in various applications. Using EXIF to visualize potholes of a city on google maps. - [What is EXIF Data in Images?](https://learnopencv.com/what-is-exif-data-in-images/) - [EXIF python explained] Find out what is EXIF and how EXIF data can be used in various applications. Using EXIF to visualize potholes of a city on google maps. - [YOLOv7 Pose vs MediaPipe in Human Pose Estimation](https://learnopencv.com/yolov7-pose-vs-mediapipe-in-human-pose-estimation/) - YOLOv7 Pose is a real time, multi person keypoint detection model capable of giving highly accurate pose estimation results. We compared it with MediaPipe Pose. - [YOLOv7 Pose vs MediaPipe in Human Pose Estimation](https://learnopencv.com/yolov7-pose-vs-mediapipe-in-human-pose-estimation/) - YOLOv7 Pose is a real time, multi person keypoint detection model capable of giving highly accurate pose estimation results. We compared it with MediaPipe Pose. - [CenterNet: Objects as Points - Anchor Free Object Detection Explained](https://learnopencv.com/centernet-anchor-free-object-detection-explained/) - CenterNet paper explanation. CenterNet: Object as Points is one of the milestones in the anchor free (anchorless) object detection algorithm. - [CenterNet: Objects as Points - Anchor Free Object Detection Explained](https://learnopencv.com/centernet-anchor-free-object-detection-explained/) - CenterNet paper explanation. CenterNet: Object as Points is one of the milestones in the anchor free (anchorless) object detection algorithm. - [Building An Automated Image Annotation Tool: PyOpenAnnotate](https://learnopencv.com/building-automated-image-annotation-tool-pyopenannotate/) - PyOpenAnnotate is an automated annotation tool for labeling images and videos using OpenCV. Try PyOpenAnnotate today from PYPI. Free annotation tool. - [Create a PyPI Package: A Guide to Building and Uploading a Pip Installable Python Package](https://learnopencv.com/building-pip-installable-package-pypi/) - Learn how to create a pip installable package. Pip, PyPi, and various build backends. We will use PyOpenAnnotate as a reference for python packaging. - [Drone Programming with Computer Vision : A Beginner's Guide](https://learnopencv.com/drone-programming-with-computer-vision/) - Drone programming: Explore the world of drone programming with computer vision! Maximize drone performance and precision for advanced applications using Python. - [Roadmap To an Automated Image Annotation Tool Using OpenCV Python](https://learnopencv.com/automated-image-annotation-tool-using-opencv-python/) - Building an automated image annotation tool using basic OpenCV algorithms. Colorspace, thresholding, and contour analysis. Annotate single class objects easily. - [Building Autonomous Vehicle in Carla: Path Following with PID Control & ROS 2](https://learnopencv.com/pid-controller-ros-2-carla/) - Learn how to build a 6DoF autonomous vehicle in CARLA using PID control and ROS 2, the PID Controller theory explained in detail with Python. - [Introduction to Model Context Protocol (MCP)](https://learnopencv.com/introduction-to-model-context-protocol/) - Model Context Protocol (MCP) provides a method to connect LLMs with different applications via a unified API using a client-server architecture. - [2D Gaussian Splatting: Geometrically Accurate Radiance Field Reconstruction](https://learnopencv.com/2d-gaussian-splatting-2dgs/) - Discover how 2D Gaussian Splatting transforms neural rendering by replacing volumetric 3D Gaussians with surface-aligned 2D disks. - [How to compile OpenCV sample code?](https://learnopencv.com/how-to-compile-opencv-sample-code/) - A simple tutorial for compiling OpenCV sample code from the command line. - [Turn your OpenCV Code into a Web API in under 10 minutes -- Part 1](https://learnopencv.com/turn-your-opencv-code-into-a-web-api-in-under-10-minutes-part-1/) - Step by step instructions for turning your OpenCV code into a web service using web2py on pythonanywhere.com - [Read an Image in OpenCV ( Python, C++ )](https://learnopencv.com/read-an-image-in-opencv-python-cpp/) - OpenCV C++ and Python examples for reading images (imread). Load color or grayscale JPG, transparent PNG / TIFF, and 16-bit / channel images. - [applyColorMap for pseudocoloring in OpenCV ( C++ / Python )](https://learnopencv.com/applycolormap-for-pseudocoloring-in-opencv-c-python/) - Use applyColorMap to pseudocolor / false color grayscale images in OpenCV. This post also explains a way to define and use custom colormaps. - [Why does OpenCV use BGR color format ?](https://learnopencv.com/why-does-opencv-use-bgr-color-format/) - One of the elements of good design is the principle of least astonishment ( a.k.a principle of least surprise). A good intuitive design makes the user not think. When you see a handle on a door, you want to pull it. When you see a door with a metal plate, you want to push it. - [OpenCV (C++ vs Python) vs MATLAB for Computer Vision](https://learnopencv.com/opencv-c-vs-python-vs-matlab-for-computer-vision/) - We often confuse our tools for our craft. Tools help you practice your craft, but they do not make you a good craftsman. A good craftsman has many different tools in her pocket, and she judiciously uses the one that is appropriate for the job. She is not married to the tools. She is married - [Using Harry Potter interactive wand with OpenCV to create magic](https://learnopencv.com/using-harry-potter-interactive-wand-with-opencv-to-create-magic/) - If you haven't been to the Wizarding World of Harry Potter or don't know what an 'interactive wand' is, you are kinda missing out on a really well designed experience that uses computer vision to create magical interactions. As this video shows, when you visit the Wizarding World at Universal Studios, you can buy a - [Training YOLOV3: Deep Learning Based Custom Object Detection](https://learnopencv.com/training-yolov3-deep-learning-based-custom-object-detector/) - Training YOLOV3 - Tutorial for training a deep learning based custom object detector with step-by-step instructions for beginners and share scripts & data - [Fast Image Downloader for Open Images V4](https://learnopencv.com/fast-image-downloader-for-open-images-v4/) - We provide a fast, multithreading based python script that helps you download the images from the publicly available Open Images V4 dataset. - [Minified OpenCV Haar and LBP Cascades](https://learnopencv.com/minified-opencv-haar-and-lbp-cascades/) - In this post, I am sharing Haar and LBP object detection cascades that have the same performance as the OpenCV cascades, but they have much smaller file sizes. I will also explain the ideas used in this minification. Why do you care about the file size? Let's say you are building a mobile app. Downloading - [Embedded Computer Vision: Which device should you choose?](https://learnopencv.com/embedded-computer-vision-which-device-should-you-choose/) - We review single board computers ( Jetson TX1, Raspberry Pi and many more ) for Computer Vision and Machine Learning applications. - [User stories : How readers of this blog are applying their knowledge to build applications](https://learnopencv.com/user-stories-how-readers-of-this-blog-are-applying-their-knowledge-to-build-applications/) - Many years back, as a student who was getting his hands dirty in the emerging field of computer vision and machine learning, I lived in a constant state of amazement. The fact that a piece of code I wrote could find circles in an image in under 10 seconds (yes, seconds, not milliseconds) made my - [Get OpenCV Build Information ( getBuildInformation )](https://learnopencv.com/get-opencv-build-information-getbuildinformation/) - In this tutorial, we will introduce a quick way to check your OpenCV build settings. If you have ever compiled or installed OpenCV, you know it can be compiled with an overwhelming number of options. For example, when installed on MacOS with Homebrew, OpenCV3 has the following options. $ brew options opencv3 --c++11 Build using - [Pytorch C++ Frontend Part II : Inputs,weights and bias](https://learnopencv.com/pytorch-c-frontend-part-ii-inputsweights-and-bias/) - In our previous blog we learnt how to install the libpytorch libraries and run the pytorch C++ frontend application. If you have not read that yet, here is the link to Part-1/1 In this blog, instead of diving right away in to coding, for the benefit of all, We will - [Technical Aspects of a Digital SLR](https://learnopencv.com/technical-aspects-of-a-digital-slr/) - Technical aspects of a DSLR camera : Focal length, f-stop, depth of field, aperture, shutter speed, ISO, image stabilization and Auto Exposure Bracketing. - [Average Faces of FIFA World Cup 2018](https://learnopencv.com/average-faces-of-fifa-world-cup-2018/) - Football has been one of the most followed sports in the past decades.This post combines the beauty of Computer Vision with the ongoing FIFA World Cup. - [PyTorch Model Inference using ONNX and Caffe2](https://learnopencv.com/pytorch-model-inference-using-onnx-and-caffe2/) - The post provides code and shows how to do inference using a Pytorch model with ONNX and Caffe2. - [Faster R-CNN Object Detection with PyTorch](https://learnopencv.com/faster-r-cnn-object-detection-with-pytorch/) - A tutorial with code for Faster R-CNN object detector with PyTorch and torchvision. Learn about R-CNN, Fast R-CNN, and Faster R-CNN. - [Install OpenCV on Windows - C++ / Python](https://learnopencv.com/install-opencv-on-windows/) - Install OpenCV on Windows in 2 clicks with our unique EXE-based installer for C++. The OpenCV installation on Windows is done using Anaconda for Python. - [Install OpenCV 4 on Ubuntu 18.04 (C++ and Python)](https://learnopencv.com/install-opencv-4-on-ubuntu-18-04/) - Learn how to build and install OpenCV from source. Bash script provided within. - [Install OpenCV 4 on macOS (C++ and Python)](https://learnopencv.com/install-opencv-4-on-macos/) - Learn how to install OpenCV on macOS Mojave and High Sierra, bash script provided within for OpenCV 4.0. - [Build and Install OpenCV 4 for Raspberry Pi](https://learnopencv.com/build-and-install-opencv-4-for-raspberry-pi/) - Raspberry Pi is a small ARM computer with a camera, a network controller, and Linux on board. That makes it a good choice for DIY computer vision projects. In this post, we will learn how to build the OpenCV library for Raspbian with native compiler on board and cross-compiler. Supported Raspberry Pi VersionsTarget hardwareARM-specific libraries - [FineTuning Gemma 3n for Medical VQA on ROCOv2](https://learnopencv.com/finetuning-gemma-3n-medical-vqa/) - A complete guide to FineTuning Gemma 3n for Medical AI. Build a specialized Radiology Visual Question Answering model using ROCOv2, Unsloth and TRL. - [Object Detection and Spatial Understanding with VLMs ft. Qwen2.5-VL](https://learnopencv.com/object-detection-with-vlms-ft-qwen2-5-vl/) - A guide to Object Detection with VLMs using Qwen2.5-VL. Go beyond simple boxes to true Spatial Understanding, Object Counting, Keypoint Detection, and more! - [TRM: Tiny AI Models beating Giants on Complex Puzzles](https://learnopencv.com/trm-tiny-ai-models-outsmarting-giants-on-complex-puzzles/) - Tiny Recursive Models (TRM), an AI approach where small networks solve complex puzzles and ARC-AGI better than giant LLMs. Learn how it works with code. - [SANA-Sprint: The One-Step Revolution in High-Quality AI Image Synthesis](https://learnopencv.com/sana-sprint-the-one-step-revolution-in-high-quality-ai-image-synthesis/) - SANA-Sprint: Get high-quality (1024, 1024) AI images in a single step! Learn about this ultra-fast diffusion model transforming image generation & real-time AI. - [MONAI: The Definitive Framework for Medical Imaging Powered by PyTorch](https://learnopencv.com/monai-medical-imaging-pytorch/) - Discover MONAI, the Medical Open Network for AI, a PyTorch-based open-source framework tailored for Deep Learning in Healthcare or Medical Imaging. - [Distributed Parallel Training: PyTorch Multi-GPU Setup in Kaggle T4x2](https://learnopencv.com/distributed-parallel-training-pytorch-multi-gpu-setup/) - Training large models on a single GPU is limited by memory constraints. Distributed training enables scalable training across multiple GPUs. - [Google I/O 2025: All you need to know](https://learnopencv.com/google-io-2025/) - Expert insights on Google I/O 2025: Gemini AI breakthroughs, Android XR evolution, new developer tools, and Google's future tech roadmap. - [Inside the GPU: A Comprehensive Guide to Modern Graphics Architecture](https://learnopencv.com/modern-gpu-architecture-explained/) - Explore the modern GPU architecture, from transistor-level design and memory hierarchies to parallel compute models and real-world GPU workloads. - [Getting Started with Qwen3 - The Thinking Expert](https://learnopencv.com/qwen3/) - Discover Qwen3, Alibaba’s open-source thinking LLM. Switch between fast replies and chain-of-thought reasoning with 128 K context, and MoE efficiency. - [Introducing BLIP3-o: The Unified Multimodal Model](https://learnopencv.com/blip3-o-multimodal-model/) - BLIP3-o: Salesforce's open-source multimodal model unifying image understanding & generation. Explore its tech, applications, and try the interactive demo! - [SmolVLA: Affordable & Efficient VLA Robotics on Consumer GPUs](https://learnopencv.com/smolvla-lerobot-vision-language-action-model/) - SmolVLA: Efficient Vision-Language-Action Model trained on Lerobot Community Data enables robots to perceive, reason and act over using VLM & Diffusion Model. - [ChatGPT ranked in the Top 20 among 1.5M students in JEE Advanced 2025](https://learnopencv.com/chatgpt-ranked-top-15-jee-advanced-2025/) - Discover how ChatGPT achieved a top 20 rank among 1.5 million students in JEE Advanced 2025. Explore AI’s impact on competitive exam preparation and future learning. - [Fine-Tuning Grounding DINO: Open-Vocabulary Object Detection](https://learnopencv.com/fine-tuning-grounding-dino/) - Object detection has traditionally been a closed-set problem: you train on a fixed list of classes and cannot recognize new ones. Grounding DINO breaks this mold, becoming an open-set, language-conditioned detector that can localize any user-specified phrase, zero-shot. Grounding DINO shatters this limitation by weaving language understanding directly into a transformer-based detector. It can localize - [The Definitive Guide to LLaVA: Inferencing a Powerful Visual Assistant](https://learnopencv.com/llava-training-a-visual-assistant/) - A complete technical breakdown of the LLaVA-1.5 multimodal visual assistant. Explore its architecture, open-source training data, and how to use the model. - [GR00T N1.5 Explained: NVIDIA’s VLA Model for Humanoids](https://learnopencv.com/gr00t-n1_5-explained/) - Dive into NVIDIA's GR00T N1.5, a groundbreaking open foundation model poised to revolutionize humanoid robotics! Discover how this advanced Vision-Language-Action (VLA) model, with its smarter architecture and innovative training using real and synthetic data (including DreamGen), is enabling robots to understand and act with unprecedented generalization and efficiency. Learn about its key performance improvements over GR00T N1 and how you can get started with the code. Ready to explore the future of intelligent robots? - [VLM for Video Understanding with Spatial and Temporal Context: NVIDIA Cosmos Reason1](https://learnopencv.com/cosmos-reason-vlm-video-vqa/) - Cosmos Reason1 VLM has excellent Physical AI and Embodied Reasoning capabilities that enables it to reason over long video sequences with grounded actions. - [Nanonets-OCR-s: Enabling Rich, Structured Markdown for Document Understanding](https://learnopencv.com/nanonets-ocr-s/) - Discover how Nanonets-OCR-s revolutionizes document processing using a VLM to convert complex visual content into structured Markdown, optimized for LLMs. - [V-JEPA 2: Meta's Breakthrough in AI for the Physical World](https://learnopencv.com/v-jepa-2-meta-world-model-robotics-guide/) - Meta's V-JEPA 2, the self-supervised world model for robotics. Learn its architecture, two-stage training, and how to run inference with a Python code example. - [Optimizing VJEPA-2: Tackling Latency & Context in Real-Time Video Classification Scripts](https://learnopencv.com/optimizing-vjepa-2-in-real-time-video-classification/) - Unlock VJEPA-2 video classification! Deep dive into SSv2, Python inference scripts, & tuning NUM_FRAMES for optimal real-time video AI performance - [MedGemma: Google's Medico VLM for Clinical QA, Imaging, and More](https://learnopencv.com/medgemma-explained/) - MedGemma: Google's medical VLM. Learn to build AI for radiology, pathology & clinical Q&A. Our guide includes code for image analysis & text reasoning. - [SigLIP 2: DeepMind's Multilingual Vision-Language Model](https://learnopencv.com/siglip-2-deepminds-multilingual-vision-language-model/) - Explore SigLIP 2, Google DeepMind's multilingual vision-language encoders with improved semantic understanding, localization and dense features. - [Fine-Tuning AnomalyCLIP: Class-Agnostic Zero-Shot Anomaly Detection](https://learnopencv.com/fine-tuning-anomalyclip-medical-anomaly-clip/) - Discover how AnomalyCLIP revolutionizes ZSAD using Object-Agnostic Prompt Learning and Glocal Context Optimization (architecture, performance, and experiments). - [Building an Agentic Browser with LangGraph: A Visual Automation and Summarization Pipeline](https://learnopencv.com/langgraph-building-a-visual-web-browser-agent/) - Learn how to build a smart visual web browser agent using LangGraph, Playwright, and Gemini. This guide explains how to create modular, stateful, and condition-driven agents. - [SmolLM3 Blueprint: SOTA 3B-Parameter LLM](https://learnopencv.com/smollm3-explained/) - SmolLM3 full architecture, training recipe, dual-mode reasoning, and post-training alignment. A guide to building and deploying this 3B-parameter model. - [SimLingo: Vision-Language-Action Model for Autonomous Driving](https://learnopencv.com/simlingo-vision-language-action-model-for-autonomous-driving/) - SimLingo unifies autonomous driving, language, and control in a camera-only model, leading CARLA benchmarks with Action Dreaming and real-time reasoning. - [Inside RoPE: Rotary Magic into Position Embeddings](https://learnopencv.com/rope-position-embeddings/) - Comprehensive guide to position embeddings: deep dive into RoPE position embeddings pair index i & d_model d experiments, and real-world LLM case studies. - [AnomalyCLIP : Harnessing CLIP for Weakly-Supervised Video Anomaly Recognition](https://learnopencv.com/anomalyclip-video-anomaly-recognition/) - Discover AnomalyCLIP, a novel framework that adapts CLIP vision-language space for video anomaly detection and recognition with hands-on implementation details. - [AI for Video Understanding: From Content Moderation to Summarization](https://learnopencv.com/ai-for-video-understanding/) - Learn how CLIP, Gemini, and Qwen transform video understanding with real-time content moderation and dynamic summarization, improving safety and accessibility. - [Video-RAG: Training-Free Retrieval for Long-Video LVLMs](https://learnopencv.com/video-rag-for-long-videos/) - Learn how Video-RAG boosts training-free and low-compute long-video understanding by pairing OCR, ASR, and open-vocabulary detection with any long-video LVLMs. - [LangGraph: Building Self-Correcting RAG Agent for Code Generation](https://learnopencv.com/langgraph-self-correcting-agent-code-generation/) - Build self-correcting AI agent using LangGraph. Creating Python code generation agent that tests its code, identifies errors, and iterates to fix them using RAG - [Inside Sinusoidal Position Embeddings: A Sense of Order](https://learnopencv.com/sinusoidal-position-embeddings/) - Explore the Sinusoidal Position Embeddings. Learn their formula, implementation, visual behavior, limitations, and experimental impact with code and charts. - [The Ultimate Guide To VLM Evaluation Metrics, Datasets, And Benchmarks](https://learnopencv.com/vlm-evaluation-metrics/) - Get a comprehensive overview of VLM Evaluation Metrics, Benchmarks and various datasets for tasks like VQA, OCR and Image Captioning. - [AI Agent in Action: Automating Desktop Tasks with VLMs](https://learnopencv.com/build-ai-agents-using-vlm/) - Learn how to build AI agent from scratch using Moondream3 and Gemini. It is a generic task based agent free from application APIs. - [Code OpenCV in Visual Studio](https://learnopencv.com/code-opencv-in-visual-studio/) - We will learn how to configure Visual Studio projects and build OpenCV applications. - [Reading and Writing Videos using OpenCV](https://learnopencv.com/reading-and-writing-videos-using-opencv/) - Learn Reading and Writing Videos using OpenCV. We discuss reading videos from file, image sequence, and webcam using OpenCV and also their syntax and options. - [Eigenface using OpenCV (C++/Python)](https://learnopencv.com/eigenface-using-opencv-c-python/) - Learn about EigenFace and Principal Component Analysis (PCA). We share code in C++ and Python. - [3D Gaussian Splatting Introduction - Paper Explanation & Training on Custom Datasets with NeRF Studio Gsplats](https://learnopencv.com/3d-gaussian-splatting/) - 3D Gaussian Splatting explained in-depth 3D Gaussian Projection, adaptive density control, tile-based rasterizer, & training custom data with NeRF-Studio Gsplat - [LightRAG: Simple and Fast Alternative to GraphRAG for Legal Doc Analysis](https://learnopencv.com/lightrag/) - LightRAG an GraphRAG alternative, leverages graph structures and text embeddings to enhance document analysis, delivering precise, context-rich insights tailored to legal needs. - [Retrieval Augmented Generation - RAG with LLMs](https://learnopencv.com/rag-with-llms/) - Retrieval Augmented Generation - RAG with LLMs powered by Langchain and the Hugging Face Transformers library for Knowledge Retrieval and Question-answering. - [MedSAM2 Explained: One Prompt to Segment Anything in Medical Imaging](https://learnopencv.com/medsam2-explained/) - Discover how MedSAM2 brings prompt-based segmentation to CT, MRI, PET, and live ultrasound, cutting annotation time by 90 % and boosting diagnostic precision. - [YOLO11 on Raspberry Pi: Optimizing Object Detection for Edge Devices](https://learnopencv.com/yolo11-on-raspberry-pi/) - YOLO11 on Raspberry Pi: Revolutionizing edge AI with real-time object detection. Learn how to deploy efficient, accurate vision systems on low-cost devices. - [Molmo VLM AI : Paper Explanation and Demo Applications - AllenAI (Ai2)](https://learnopencv.com/molmo-vlm/) - Molmo VLM: Explore how this open-source VLM excels in pointing, counting, VQA, and integrates with SAM for precise segmentation and groundbreaking applications. - [ColPali: Enhancing Financial Report Analysis with Multimodal RAG and Gemini](https://learnopencv.com/multimodal-rag-with-colpali/) - ColPali integration with Gemini marks a significant leap in GenAI, enhancing multimodal document retrieval quality while preserving document structure by a huge margin. - [Vision Language Action Models (VLA) Overview: LeRobot Policies Demo](https://learnopencv.com/vision-language-action-models-lerobot-policy/) - Vision Language Actions Models enables robots to perceive, reason and act over complex tasks and perform precise dexterous movements using VLM & Diffusion Model - [ROS 2 and Carla Setup Guide for Ubuntu 22.04](https://learnopencv.com/ros2-and-carla-setup-guide/) - In this article we will be giving a complete ROS2 and Carla setup guide for Ubuntu 22.04. We will also showcase how to use Docker for robotics. - [FramePack: Video Diffusion, but feels like Image Diffusion](https://learnopencv.com/framepack-video-diffusion/) - Run powerful AI video generation locally! FramePack enables 30fps video on 6GB VRAM by fixing context limits. Understand its architecture in this blog post. - [Model Weights File Formats in Machine Learning](https://learnopencv.com/model-weights-file-formats-in-machine-learning/) - Discover the widely used model weights file formats in machine learning, including .pt, .ckpt, .h5, .onnx, .safetensors, .gguf, .tflite, .engine, and .mlmodel. - [Understanding Iterative Closest Point (ICP) Algorithm with Code](https://learnopencv.com/iterative-closest-point-icp-explained/) - Iterative Closest Point (ICP) explained with code in Python and Open3D which is a widely used classical algorithm for 2D or 3D point cloud registration - [Unsloth: A Guide from Basics to Fine-Tuning Vision Models](https://learnopencv.com/unsloth-guide-efficient-llm-fine-tuning/) - Learn everything about fine-tuning large language models with Unsloth! Explore QLoRA, PEFT, Dynamic 2.0 GGUFss, and more in this all-in-one professional guide. - [DINOv2 by Meta: A Self-Supervised foundational vision model](https://learnopencv.com/dinov2-self-supervised-vision-transformer/) - DINOv2: Meta's Self-Supervised vision transformer for groundbreaking image understanding. Learn how it surpasses DINO with enhanced performance and efficiency. - [Batch Normalization and Dropout: A Combined Regularization Approach](https://learnopencv.com/batch-normalization-and-dropout-as-regularizers/) - Learn how to effectively combine Batch Normalization and Dropout as Regularizers in Neural Networks. Explore the challenges, best practices, and scenarios. - [Gemma 3: A Comprehensive Introduction](https://learnopencv.com/gemma-3/) - Gemma 3: A comprehensive introduction to its features, architecture, and use cases. Explore its multimodal capabilities, scalability, and key innovations. - [Google’s A2A Protocol: Here’s What You Need to Know](https://learnopencv.com/googles-a2a-protocol-heres-what-you-need-to-know/) - A2A protocol by Google enables seamless communication between AI agents using a unified messaging standard for scalable multi-agent systems. - [Beginner's Guide to Embedding Models](https://learnopencv.com/embedding-models-explained/) - Learn how embedding models work across text, images, audio, and video. Explore their types, general functioning, and real-world applications in great detail. - [MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors](https://learnopencv.com/mast3r-slam-realtime-dense-slam-explained/) - MASt3R-SLAM operates real-time and achieves SOTA results by employing novel techniques in pipeline for matching, fusion and optimization by using MASt3R Priors - [Mastering All YOLO Models from YOLOv1 to YOLOv12: Papers Explained (2025)](https://learnopencv.com/mastering-all-yolo-models/) - Exploring all YOLO models from YOLOv1 to YOLO11 including YOLO-R, YOLOX, and YOLO-NAS - [NVIDIA SANA: Fast, High-Resolution Text-to-Image Generation Explained](https://learnopencv.com/nvidia-sana-image-generation-model/) - Discover NVIDIA SANA: The breakthrough AI model with breath-taking image generation quality. Learn about its speed, efficiency & accessibility. - [Diving into the Nodes: An Introduction to ComfyUI for Stable Diffusion](https://learnopencv.com/introduction-to-comfyui-for-stable-diffusion/) - ComfyUI is a visual, node-based interface for Diffusion and other AI workflows, enabling easy, customizable image generation with powerful model control. - [DDIM: The Faster, Improved Version of DDPM for Efficient AI Image Generation](https://learnopencv.com/understanding-ddim/) - Discover DDIM, a faster alternative to DDPM and other diffusion models for image generation. Includes simple explanations, code snippets - [Introduction to LiDAR SLAM: LOAM and LeGO-LOAM Paper and Code Explanation with ROS 2 Implementation](https://learnopencv.com/lidar-slam-with-ros2/) - In this article we covered the fundamental of LiDAR SLAM, went through the LOAM and LeGO-LOAM papers with code explanation with ROS2 implementation. - [RF-DETR by Roboflow: Speed Meets Accuracy in Object Detection](https://learnopencv.com/rf-detr-object-detection/) - Explore RF-DETR: Roboflow's object detection model using DINOv2/LW-DETR to fix DETR limits. Learn architecture, performance & fine-tuning. - [Qwen2.5-Omni: A Real-Time Multimodal AI](https://learnopencv.com/qwen2-5-omni/) - Qwen2.5-Omni Real-Time Multimodal Model. Learn how its Thinker-Talker architecture enables unified text and speech output across text, audio, image, and video. - [Fine-Tuning Gemma 3 VLM using QLoRA for LaTeX-OCR Dataset](https://learnopencv.com/fine-tuning-gemma-3/) - Fine-Tuning Gemma 3 VLM using QLoRA for LaTeX-OCR Dataset. Learn how to efficiently fine-tune the model on the LaTeX_OCR for improved image-to-text performance. - [Introduction to GPT-4o Image Generation - Here’s What You Need to Know](https://learnopencv.com/gpt-4o-image-generation/) - GPT-4o image generation is now native to ChatGPT, enabling seamless text-to-image creation, edits, and style transfer for design, education, and lot more! - [YOLO Loss Function Part 1: SIoU and Focal Loss](https://learnopencv.com/yolo-loss-function-siou-focal-loss/) - YOLO models are very famous object detection models, and here we discuss about the inner workings of the YOLO loss function and theirpytorch implementations. - [MASt3R and MASt3R-SfM Explanation: Image Matching and 3D Reconstruction Results](https://learnopencv.com/mast3r-sfm-grounding-image-matching-3d/) - ​MASt3R redefines image matching by grounding it in 3D, enhancing accuracy and efficiency in structure-from-motion tasks scaling to larger scenes. - [VGGT: Visual Geometry Grounded Transformer - For Dense 3D Reconstruction](https://learnopencv.com/vggt-visual-geometry-grounded-transformer-3d-reconstruction/) - VGGT is a feed forward network that infers 3D scene attributes such as camera parameters, depth maps, points maps and 3D point tracks in a single forward pass. - [Contrastive Learning - SimCLR and BYOL (With Code Example)](https://learnopencv.com/contrastive-learning-simclr-and-byol-with-code-example/) - Learn Contrastive Learning with SimCLR and BYOL, explore their algorithms, and get practical code examples for implementation. - [Agentic AI: An Introduction to Autonomous Intelligent Systems](https://learnopencv.com/agentic-ai/) - Explore Agentic AI and learn how to build no-cost Agentic RAG applications using CrewAI and Phidata frameworks to enhance AI capabilities and automation. - [YOLOv12: Object Detection with Attention](https://learnopencv.com/yolov12/) - YOLOv12, another addition to YOLO object detection series by Ultralytics, marks it's importance by introducing attention mechanism instead of using classic CNN. - [GraphRAG: The Practical Guide for Cost-Effective Document Analysis with Knowledge Graphs](https://learnopencv.com/graphrag-explained-knowledge-graphs-medical/) - GraphRAG integrates structured Knowledge Graphs (KGs) enabling LLM to reason over complex, multi-hop queries and provide accurate and context-rich responses. - [Handwritten Text Recognition using OCR](https://learnopencv.com/handwritten-text-recognition-using-ocr/) - Handwritten Text Recognition using OCR by fine tuning the TrOCR model on Goodnotes Handwritten Text dataset using the Hugging Face Transformers library. - [DUSt3R: Geometric 3D Vision Made Easy : Explanation and Results](https://learnopencv.com/dust3r-geometric-3d-vision/) - DUSt3R, a novel paradigm in 3D reconstruction, is a game-changer with its unified model architecture, outperforming existing SfM and MVS baselines like COLMAP. - [WhisperX Automatic Speech Recognition (ASR) with Nemo Speaker Diarization : Speech-to-Text](https://learnopencv.com/automatic-speech-recognition/) - Automatic Speech Recognition (ASR) with OpenAI Whisper and Nvidia NeMo Toolkit, delivers high-accuracy transcription and sophisticated diarization capabilities. - [OmniParser: Vision Based GUI Agent](https://learnopencv.com/omniparser-vision-based-gui-agent/) - OmniParser is a UI screen parsing pipeline combining a YOLO for icon detection and a fine-tuned Florence 2 model for icon recognition and description. - [MatAnyone Explained: Consistent Memory for Better Video Matting](https://learnopencv.com/matanyone-for-better-video-matting/) - Learn how MatAnyone uses AI and consistent memory banks to deliver precise video matting with smooth, accurate alpha mattes for filmmakers and editors. - [Diffusion Models for Image Generation - A Comprehensive Guide](https://learnopencv.com/image-generation-using-diffusion-models/) - Diffusion models for Image Generation and art generation like Stable Diffusion, Dall-E 2, Imagen, and Midjourney are the new trend in generative modeling. - [Depth Pro: The Sharp Monocular Metric Depth Estimation from Apple Explanation and Applications](https://learnopencv.com/depth-pro-monocular-metric-depth/) - Apple Depth Pro is a powerful Monocular Metric Depth Estimation model producing high-resolution depth maps with sharp boundaries—extremely fast and accurate. - [Fine-Tuning YOLOv12: Comparison with YOLOv11 & Darknet-Based YOLOv7](https://learnopencv.com/fine-tuning-yolov12/) - Fine-tuning YOLOv12 vs. YOLOv11 vs. Darknet-Based YOLOv7: A comparison on HRSC2016-MS, dataset preprocessing, analyzing mAP scores, and real-world inference. - [YOLO11: Redefining Real-Time Object Detection](https://learnopencv.com/yolo11/) - YOLO11, the latest YOLO model from Ultralytics, delivers SOTA speed and efficiency in object detection. Discover what’s new, how it outperforms YOLOv12. - [Stable Diffusion 3.5: Paper Explanation and Inference](https://learnopencv.com/stable-diffusion-3/) - Stable Diffusion 3.5 in-depth explanation and Inference with an intuitive approach for topics like Latent Diffusion and Flow Matching. - [Fine-tuning Stable Diffusion 3.5: UI images](https://learnopencv.com/fine-tuning-stable-diffusion-3-5m/) - Fine-tuning Stable Diffusion 3.5 for flat-UI image generation. Techniques like DreamBooth and LoRA, dataset preparation, and configuration tips are discussed. - [Getting Started with YOLOv5 Instance Segmentation](https://learnopencv.com/yolov5-instance-segmentation/) - YOLOv5 Instance Segmentation: Exceptionally Fast, Accurate for Real-Time Computer Vision on Images and Videos, Ideal for Deep Learning. - [Training CLIP Model from Scratch for an Fashion Image Retrieval App](https://learnopencv.com/clip-model/) - Contrastive Language Image Pretraining (CLIP) training from scratch for fashion image retrieval, with precise text-visual feature similarity matching. - [Object Detection on Edge Device: Deploying YOLOv8 on Luxonis OAK-D-Lite - Pothole Datset](https://learnopencv.com/object-detection-on-edge-device/) - Object Detection on Edge Device - Deployment tutorial for running fine-tuned YOLOv8 on OAK-D-Lite device with DepthAI pipeline for Pothole Detection. - [YOLOv9 Instance Segmentation on Medical Dataset](https://learnopencv.com/yolov9-instance-segmentation-on-medical-dataset/) - YOLO Instance Segmentation assists medical expertise in efficient and accurate segmentation of the ROIs in medical image analysis offering reliable detection. - [Deep Learning with OpenCV DNN Module: A Definitive Guide](https://learnopencv.com/deep-learning-with-opencvs-dnn-module-a-definitive-guide/) - Learn OpenCV DNN Module and the different Deep Learning functionalities, models & frameworks it supports. See Image Classification/Object Detection in action. - [The Annotated NeRF - Training on Custom Dataset from Scratch in Pytorch](https://learnopencv.com/annotated-nerf-pytorch/) - This article explores the inner workings of NeRF, walks through the NeRF PyTorch implementation from scratch, and covers training NeRF on a custom dataset. - [Object Insertion in Gaussian Splatting: Paper Explanation and Training of MCMC in Gsplat](https://learnopencv.com/object-insertion-in-gaussian-splatting/) - Object Insertion in gaussian splatting trained using MCMC + Bilateral Grid on NeRF Studio gsplats. 3D Gaussian Splatting as MCMC paper explained in detail. Mask based Gaussian Splatting training for object scene. - [Object Keypoint Similarity in Keypoint Detection](https://learnopencv.com/object-keypoint-similarity/) - Object Keypoint Similarity (OKS) is used to estimate a similarity measure across two given sets of keypoints, analogous to what Intersection over Union does. - [Sapiens: Foundation for Human Vision Models by Meta](https://learnopencv.com/sapiens-human-vision-models/) - Sapiens Human Vision Model by Meta achieve state-of-the-art performance in tasks like 2D pose estimation, body-part segmentation, normal and depth estimation. - [What is Face Detection? Ultimate Guide 2025 + Model Comparison](https://learnopencv.com/what-is-face-detection-the-ultimate-guide/) - What is Face Detection? It's a technique to find the location of faces in an image or video. With performance comparison + Top 9 algorithms for Face Detection - [Image Captioning using ResNet and LSTM](https://learnopencv.com/image-captioning/) - Image captioning using ResNet and LSTM: Learn how this model bridges computer vision and NLP to generate captions, powering accessibility, SEO, and robotics. - [SimSiam: Streamlining SSL with Stop-Gradient Mechanism](https://learnopencv.com/simsiam/) - SimSiam, leveraging Stop-Gradient and Siamese NNs, excels in Non-Collapsing Representation Learning and Implicit Optimization Dynamics for Self-Supervision. - [Disparity Estimation Using Deep Learning](https://learnopencv.com/disparity-estimation-using-deep-learning/) - Learn to solve Depth estimation problems using stereo vision and deep learning-based approaches for disparity estimation. And capture 3D Images. - [Disparity Estimation Using Deep Learning](https://learnopencv.com/disparity-estimation-using-deep-learning/) - Learn to solve Depth estimation problems using stereo vision and deep learning-based approaches for disparity estimation. And capture 3D Images. - [Integrating ADAS with Keypoint Feature Pyramid Network for 3D LiDAR Object Detection](https://learnopencv.com/3d-lidar-object-detection/) - In this research experiment, we will train a keypoint feature pyramid network for 3D LiDAR Object Detection on KITTI 360 Vision point-clouds for self-driving with RGB cameras and 3D LiDAR fusion. - [Introduction to Ultralytics Explorer API](https://learnopencv.com/ultralytics-explorer-api/) - Explore image datasets using Ultralytics Explorer API, offering Python APIs and GUI for similarity searches, AI queries, and efficient data analysis and more. - [FLUX AI Image Generation: Experimenting with the Parameters](https://learnopencv.com/flux-ai-image-generator/) - Utilize FLUX AI image generation model, an open-source image generation tool, to create stunning images for diverse applications, from YouTube thumbnails to UI designs. - [Face Morph Using OpenCV -- C++ / Python](https://learnopencv.com/face-morph-using-opencv-cpp-python/) - In this tutorial we will learn how to morph one face into another using OpenCV. I have chosen to use the photos of the top three American Presidential candidates, but this is not a political post and I have no political agenda. And yes, that is the prettiest picture of Donald Trump I could find! - [Moving Object Detection with OpenCV using Contour Detection and Background Subtraction](https://learnopencv.com/moving-object-detection-with-opencv/) - Discover moving object detection using OpenCV, blending contour detection with background subtraction for real-time application in security and traffic. - [Geometry of Image Formation](https://learnopencv.com/geometry-of-image-formation/) - In this post, we will explain the image formation from a geometrical point of view. Specifically, we will cover the math behind how a point in 3D gets projected on the image plane. This post is written with beginners in mind but it is mathematical in nature. That said, all you need to know is - [A Step-by-Step Tutorial on Image Segmentation using Tensorflow Hub](https://learnopencv.com/image-segmentation-tensorflow-hub/) - In this post, we will learn how to perform semantic image segmentation using Tensorflow Hub using the HRNet model which has been pretrained on CamVid dataset. - [Implementing an MLP in TensorFlow & Keras](https://learnopencv.com/implementing-mlp-tensorflow-keras/) - In this post, we will learn how to Implement a Feed-Forward Neural Network for performing Image Classification on the MNIST dataset in Keras. - [Install OpenCV Docker Image on Ubuntu, MacOS or Windows](https://learnopencv.com/install-opencv-docker-image-ubuntu-macos-windows/) - Guide to Install OpenCV 4.0 and 3.4.1 Docker Images on Ubuntu, MacOS, and Windows. The images also come preloaded with dlib. - [Install OpenCV 3.4.4 on Ubuntu 16.04 (C++ and Python)](https://learnopencv.com/install-opencv-3-4-4-on-ubuntu-16-04/) - In this post we will provide a bash script for installing OpenCV 3.4.4 on Ubuntu 16.04 - [Introduction to Speech to Speech: Most Efficient Form of NLP](https://learnopencv.com/speech-to-speech/) - Speech to Speech lets computers talk with us naturally! Discover its magic, from voice detection to responses! See how AI powers real-time interactions. - [Recommendation System using Vector Search with Qdrant](https://learnopencv.com/recommendation-system-using-vector-search/) - Recommendation System Using Vector Search: Learn how to build a movie recommendation system with Qdrant using sparse vector search for accurate results. - [Introduction to Feature Matching Using Neural Networks](https://learnopencv.com/feature-matching/) - Feature matching using deep learning enhances panoramas, generates 3D Avaters, and recognizes faces, making computer vision tasks accurate and reliable. - [YOLOv10: The Dual-Head OG of YOLO Series](https://learnopencv.com/yolov10/) - YOLOv10 upgrades object detection with dual-head architecture and NMS-free training, making it faster and more accurate for real-time tasks. - [Mastering Recommendation System: A Complete Guide](https://learnopencv.com/recommendation-system/) - Recommendation system (recommender system) use traditional ml and deep learning techniques to suggest content you’ll love. Learn about their types and workflow - [SDXL Inpainting: Fusing Image Inpainting with Stable Diffusion](https://learnopencv.com/sdxl-inpainting/) - SDXL inpainting, the AI Magician that transforms image inpainting and creative editing with Stable Diffusion. Unlock new possibilities with magic! - [YOLOv9: Advancing the YOLO Legacy](https://learnopencv.com/yolov9-advancing-the-yolo-legacy/) - YOLOv9 advances object detection with innovative Programmable Gradient Information(PGI) and Generalized ELAN, boosting efficiency and accuracy. - [Build an AI Fitness Trainer Using MediaPipe For Squat Analysis](https://learnopencv.com/ai-fitness-trainer-using-mediapipe/) - AI fitness trainer - Build aapplication that analyzes squats using MediaPipe’s Pose solution and prompts appropriate feedback. - [NVIDIA AI Summit 2024 - India Overview](https://learnopencv.com/nvidia-ai-summit-2024-india-overview/) - NVIDIA AI Summit 2024 - India, covered various topics in AI starting from India's powerful position in AI software to upcoming companies in GPU hardware. - [Exploring DINO: Self-Supervised Transformers for Road Segmentation with ResNet50 and U-Net](https://learnopencv.com/fine-tune-dino-self-supervised-learning-segmentation/) - This article explores the history of self-supervised learning, introduces DINO Self-Supervised Learning, and shows how to fine-tune DINO for road segmentation - [Convolutional Neural Network (CNN): A Complete Guide](https://learnopencv.com/understanding-convolutional-neural-networks-cnn/) - Convolutional Neural Network (CNN) Master it with our complete guide. Dive deep into CNNs and elevate your understanding. - [DETR: Overview and Inference](https://learnopencv.com/detr-overview-and-inference/) - DETR, is an efficient Transformer-based Object Detection model that eliminates the need for priors like anchor boxes and NMS, resulting in improved metrics. - [Fine-tuning Faster R-CNN on Sea Rescue Dataset - Small Object Detection: PyTorch](https://learnopencv.com/fine-tuning-faster-r-cnn/) - Fine-tuning Faster R-CNN on the SeaRescue dataset revolutionizes small object detection in maritime scenarios, potentailly saving countless lives. - [CVPR 2024 Key Research & Dataset Papers - Part 2](https://learnopencv.com/cvpr-2024-research-papers/) - CVPR 2024 research papers were promising, highlighting the latest trends and advancements in the fields of computer vision, Gen AI, and robotics applications. - [CVPR 2024: An Overview and Key Papers](https://learnopencv.com/cvpr2024/) - CVPR 2024: Dive into the latest AI and computer vision innovations with top papers on generative image dynamics, advanced 3D modeling, video editing, and more. - [Document Segmentation Using Deep Learning in PyTorch](https://learnopencv.com/deep-learning-based-document-segmentation-using-semantic-segmentation-deeplabv3-on-custom-dataset/) - Document Scanning is a background segmentation problem. We train a DeepLabv3 in PyTorch, a semantic segmentation architecture to solve Document Segmentation. - [Document Segmentation Using Deep Learning in PyTorch](https://learnopencv.com/deep-learning-based-document-segmentation-using-semantic-segmentation-deeplabv3-on-custom-dataset/) - Document Scanning is a background segmentation problem. We train a DeepLabv3 in PyTorch, a semantic segmentation architecture to solve Document Segmentation. - [Document Segmentation Using Deep Learning in PyTorch](https://learnopencv.com/deep-learning-based-document-segmentation-using-semantic-segmentation-deeplabv3-on-custom-dataset/) - Document Scanning is a background segmentation problem. We train a DeepLabv3 in PyTorch, a semantic segmentation architecture to solve Document Segmentation. - [Document Segmentation Using Deep Learning in PyTorch](https://learnopencv.com/deep-learning-based-document-segmentation-using-semantic-segmentation-deeplabv3-on-custom-dataset/) - Document Scanning is a background segmentation problem. We train a DeepLabv3 in PyTorch, a semantic segmentation architecture to solve Document Segmentation. - [GradCAM - Enhancing Neural Network Interpretability in the Realm of Explainable AI](https://learnopencv.com/intro-to-gradcam/) - GradCAM aims to establish a relationship between the activation feature maps and the classifier output, enhancing model interpretability in neural networks. - [Enhancing Image Segmentation using U2-Net: An Approach to Efficient Background Removal](https://learnopencv.com/u2-net-image-segmentation/) - U2-Net is a simple yet powerful deep-learning-based semantic segmentation model that enhances background removal using the power of ReSidual-U (RSU) blocks. - [The Future of Image Recognition is Here: PyTorch Vision Transformers](https://learnopencv.com/the-future-of-image-recognition-is-here-pytorch-vision-transformer/) - Vision Transformer implementation from scratch using the PyTorch deep learning library and training it on the ImageNet dataset. Learn self-attention mechanism. - [SAM 2 - Promptable Segmentation for Images and Videos](https://learnopencv.com/sam-2/) - SAM 2 (Segment Anything Model 2) is the next iteration in the SAM family of models for Promptable Visual Segmentation on images and videos in real-time. - [Fine Tuning Whisper on Custom Dataset](https://learnopencv.com/fine-tuning-whisper-on-custom-dataset/) - Fine tuning Whisper on a custom dataset involving Air Traffic Control audio and diving deep into the dataset & training code to understand the process. - [Train YOLOv8 on Custom Dataset - A Complete Tutorial](https://learnopencv.com/train-yolov8-on-custom-dataset/) - Train YOLOv8 on a custom pothole detection dataset. Training YOLOv8 Nano, Small, & Medium models and running inference for pothole detection on unseen videos. - [Torchvision Semantic Segmentation - PyTorch for Beginners](https://learnopencv.com/pytorch-for-beginners-semantic-segmentation-using-torchvision/) - Torchvision Semantic Segmentation - Classify each pixel in the image into a class. We use torchvision pretrained models to perform Semantic Segmentation. - [Introduction to ROS 2 (Robot Operating System 2): Tutorial on ROS 2 Working, DDS, ROS 1 RMW, Topics, Nodes, Publisher, Subscriber in Python](https://learnopencv.com/robot-operating-system-introduction/) - This is a beginner friendly introduction to ROS2(Robot Operating System 2) in Python.We talked about DDS, ROS1 RMW, Publisher,Subscriber and SLAM project in ROS2 - [Mask RCNN Pytorch - Instance Segmentation](https://learnopencv.com/mask-r-cnn-instance-segmentation-with-pytorch/) - Here we discuss the theory behind Mask RCNN Pytorch and how to use the pre-trained Mask R-CNN model in PyTorch. Part of our series on PyTorch for Beginners - [Transfer Learning For Pytorch Image Classification](https://learnopencv.com/image-classification-using-transfer-learning-in-pytorch/) - Transfer Learning with Pytorch for precise image classification: Explore how to classify ten animal types using the CalTech256 dataset for effective results. - [Training Neural Networks for Beginners](https://learnopencv.com/how-to-train-neural-networks-for-beginners/) - In this post, we cover the essential elements required for training Neural Networks for an image classification problem with emphasis on fundamental concepts. - [Pre Trained Models for Image Classification - PyTorch for Beginners](https://learnopencv.com/pytorch-for-beginners-image-classification-using-pre-trained-models/) - Pre trained models for Image Classification - How we can use TorchVision module to load pre-trained models and carry out model inference to classify an image. - [Fine-Tuning YOLOv10 Models on Custom Dataset for Kidney Stone Detection](https://learnopencv.com/fine-tuning-yolov10/) - This comprehensive research article explores fine-tuning YOLOv10 models on a custom dataset for kidney stone detection in medical diagnosis. - [Fine-Tuning YOLOv9 Models on Custom Dataset](https://learnopencv.com/fine-tuning-yolov9/) - This experiment-oriented research article explains the procedure for fine-tuning YOLOv9 models on a custom dataset, specifically on satellite imagery. - [Building MobileViT Image Classification Model from Scratch In Keras 3](https://learnopencv.com/mobilevit-keras-3/) - Learn the intricacies of the MobileViT model and build it from scratch using Keras 3 for efficient image classification on resource-constrained devices. - [3D LiDAR Visualization using Open3D: A Case Study on 2D KITTI Depth Frames for Autonomous Driving](https://learnopencv.com/3d-lidar-visualization/) - Explore the impact of 3D LiDAR sensor in driver autonomy, with a deep dive into 3D point cloud visualization and its role in advanced driver assistance systems. - [Stereo Vision in ADAS: Pioneering Depth Perception Beyond LiDAR](https://learnopencv.com/adas-stereo-vision/) - ADAS stereo vision is one of the most crucial components for depth perception. We have shown the fine-tuning process of STereo TRansformer model for ADAS here. - [Advanced Driver Assistance Systems (ADAS): Empowering Drivers](https://learnopencv.com/advanced-driver-assistance-systems/) - Advanced Driver Assistance Systems: Explore the rise of ADAS in enhancing vehicle safety & driving experience, using cutting-edge sensor-fusion and automation - [Text Summarization using T5: Fine-Tuning and Building Gradio App](https://learnopencv.com/text-summarization-using-t5/) - Text Summarization using T5: Uncover advanced NLP techniques and applications with the transformative T5 model, shaping the future of concise, AI-driven content - [An In-Depth Guide to Denoising Diffusion Probabilistic Models DDPM - Theory to Implementation](https://learnopencv.com/denoising-diffusion-probabilistic-models/) - DDPMAn in-depth explanation of the theory and math behind denoising diffusion probabilistic models and implementing them from scratch in PyTorch. - [Depth Anything: Accelerating Monocular Depth Perception](https://learnopencv.com/depth-anything/) - Depth Anything uses monocular depth perception technique to perceive depth. In this research article, the architecture along with inference results and mathematical expressions have been explored. - [Deciphering LLMs: From Transformers to Quantization](https://learnopencv.com/deciphering-llms/) - LLMs typically referred to as "Large Language Models" are advanced artificial intelligence models designed to understand and generate human-like text. - [Fine Tuning T5: Text2Text Transfer Transformer for Building a Stack Overflow Tag Generator](https://learnopencv.com/fine-tuning-t5/) - Fine Tuning T5 transformer for Stack Overflow tag generation involves dataset prep, training, and inference, all covered in this comprehensive guide - [Automatic License Plate Recognition using Deep Learning](https://learnopencv.com/automatic-license-plate-recognition-using-deep-learning/) - Automatic License Plate Recognition ALPR/ANPR - Implementation using YOLOv4 as detector and PaddleOCR as OCR with DeepSORT tracker for performance improvement - [Automatic License Plate Recognition using Deep Learning](https://learnopencv.com/automatic-license-plate-recognition-using-deep-learning/) - Automatic License Plate Recognition ALPR/ANPR - Implementation using YOLOv4 as detector and PaddleOCR as OCR with DeepSORT tracker for performance improvement - [Introducing YOLO-NAS Pose: A Leap in Pose Estimation Technology](https://learnopencv.com/yolo-nas-pose/) - YOLO-NAS Pose: Deci's latest in Pose Estimation, blending exceptional accuracy and speed for advancements in healthcare, sports, and robotics - [Train YOLO NAS on Custom Dataset](https://learnopencv.com/train-yolo-nas-on-custom-dataset/) - Train YOLO NAS on custom dataset, analyze the results, and run inference on images and videos. Train YOLO NAS Small, Medium, and Large models. - [Meet YOLO-NAS: New YOLO Object Detection Model Beats YOLOv6 & YOLOv8](https://learnopencv.com/yolo-nas/) - YOLO-NAS is the new real-time SOTA object detection model. YOLO-NAS models outperform YOLOv7, YOLOv8 & YOLOv6 3.0 models in terms of mAP and inference latency. - [Comparing KerasCV YOLOv8 Models on the Global Wheat Data 2020](https://learnopencv.com/comparing-kerascv-yolov8-models/) - Comparing KerasCV YOLOv8 Models by fine-tuning the Global Wheat Data Challenge. We will compare the performance of these models against Weighted Boxes Fusion. - [Animal Pose Estimation: Fine-tuning YOLOv8 Pose Models](https://learnopencv.com/animal-pose-estimation/) - Animal pose estimation can be performed by fine-tuning pre-trained YOLOv8 pose models for analyzing animal postures, and performing specific keypoint analysis. - [Train YOLOv8 Instance Segmentation on Custom Data](https://learnopencv.com/train-yolov8-instance-segmentation/) - YOLOv8 instance segmentation custom training allows us to fine tune the models according to our needs and get the desired performance while inference. - [Object Detection using KerasCV YOLOv8](https://learnopencv.com/object-detection-using-kerascv-yolov8/) - Learn how to use the KerasCV YOLOv8 model for object detection and train it on a real-life traffic light detection dataset. - [YOLOv8 : Comprehensive Guide to State Of The Art Object Detection](https://learnopencv.com/ultralytics-yolov8/) - YOLOv8 models for object detection, image segmentation, and image classification. Comparison with previous YOLO models and inference on images and videos. - [Performance Comparison of YOLO Object Detection Models - An Intensive Study](https://learnopencv.com/performance-comparison-of-yolo-models/) - We present a etailed Comparison of YOLO Models. Which YOLO model is the fastest? What about inference speed on CPU vs GPU? Which YOLO model is the most accurate? - [YOLOv6 Custom Dataset Training - Underwater Trash Detection](https://learnopencv.com/yolov6-custom-dataset-training/) - YOLOv6 custom dataset training: Learn how we trained the Nano, Small, and Large models on a custom Underwater Trash Detection. - [YOLOv7 Object Detection Paper Explanation & Inference](https://learnopencv.com/yolov7-object-detection-paper-explanation-and-inference/) - YOLOv7 paper explanation with object detection Inference test. Learn how to use YOLOv7 GitHub repository. YOLOv7 Pose detection included. - [Fine Tuning YOLOv7 on Custom Dataset](https://learnopencv.com/fine-tuning-yolov7-on-custom-dataset/) - In this blog post, we are fine tuning YOLOv7 object detection model on a custom dataset to detect pot holes on roads in real time. - [Introduction to Intel OpenVINO Toolkit](https://learnopencv.com/introduction-to-intel-openvino-toolkit/) - OpenVino Toolkit: Discover how to install & execute pre-trained models on Intel CPUs utilizing the Intel OpenVino Toolkit for optimized near real-time performance - [Introduction to Intel OpenVINO Toolkit](https://learnopencv.com/introduction-to-intel-openvino-toolkit/) - OpenVino Toolkit: Discover how to install & execute pre-trained models on Intel CPUs utilizing the Intel OpenVino Toolkit for optimized near real-time performance - [Dreambooth using Diffusers](https://learnopencv.com/dreambooth-using-diffusers/) - Dreambooth training and the Hugging Face Diffusers library allow us to train Stable Diffusion models with just a few lines of code to generate our own images. - [Introduction to Hugging Face Diffusers](https://learnopencv.com/hugging-face-diffusers/) - The Hugging Face Diffusers library is a one-stop shop for image generation using Stable Diffusion models for text-to-image, image-to-image, & image inpainting. - [Mouse and Trackbar in OpenCV GUI](https://learnopencv.com/mouse-and-trackbar-in-opencv-gui/) - Learn about mouse and trackbar in OpenCV. Explore how to annotate and resize images using mouse and trackbar functionalities available in OpenCV GUI. - [Image Thresholding in OpenCV](https://learnopencv.com/opencv-threshold-python-cpp/) - Learn about image thresholding in OpenCV. Also, learn about different types of thresholding in OpenCV. - [From Pixels to Paintings: The Rise of Midjourney AI Art](https://learnopencv.com/rise-of-midjourney-ai-art/) - Discover Midjourney Ai Art, a revolutionary AI program that generates high-quality images with an unique artistic style. Perfect for artists and creatives. - [Stable Diffusion - A New Paradigm in Generative AI](https://learnopencv.com/stable-diffusion-generative-ai/) - Stable Diffusion takes AI Image Generation to the next level. Learn how Stable Diffusion works under the hood during training and inference in our latest post. - [InstructPix2Pix - Edit Images With Prompts](https://learnopencv.com/instructpix2pix/) - InstructPix2Pix is a new Stable Diffusion based model that can edit images using text prompts only. It can change backgrounds, hairstyle using prompts. - [ControlNet - Achieving Superior Image Generation Results](https://learnopencv.com/controlnet/) - ControlNet models give users more control while generating images by providing Canny edge, HED edge, segmentation maps, and even pose detection models. - [Fine-Tuning LLMs using PEFT](https://learnopencv.com/fine-tuning-llms-using-peft/) - Fine-tuning LLMs leverages the vast knowledge acquired by LLMs and tailors it towards specialized tasks. Imagine an LLM pre-trained on a massive corpus of text. - [Annotating Images Using OpenCV](https://learnopencv.com/annotating-images-using-opencv/) - Learn about annotating images using OpenCV. Also learn about the different functions and ways to annotate images. - [Image Translation and Rotation Using OpenCV](https://learnopencv.com/image-rotation-and-translation-using-opencv/) - Learn about image translation and rotation using OpenCV. Also, learn about the syntax and methods used to rotate and translate an image. - [YOLO Loss Function Part 2: GFL and VFL Loss](https://learnopencv.com/yolo-loss-function-gfl-vfl-loss/) - Explore advanced YOLO loss function, GFL and VFL, for improved object detection, highlighting key design choices, solutions, and PyTorch implementations. - [PyTorch Tutorial For Beginners: All the Basics](https://learnopencv.com/pytorch-for-beginners-basics/) - Pytorch Tutorial For Beginners -In this post we will discuss what PyTorch is and why should you learn it. We will also discuss about Tensors in some depth - [Object Detection Made Easy with TensorFlow Hub: Step-by-Step Tutorial](https://learnopencv.com/object-detection-tensorflow-hub/) - Object detection with TensorFlow Hub is a powerful tool, and in this guide, we'll delve into using pre-trained models, specifically the EfficientDet D4 model. - [Unlock the Power of Fine-Tuning Pre-Trained Models in TensorFlow & Keras](https://learnopencv.com/fine-tuning-pre-trained-models-tensorflow-keras/) - In this post, you will learn how to unlock the power of fine-tuning pre-trained models to customize them for your own datasets. - [Image Classification using Pre-Trained ImageNet Models in TensorFlow & Keras](https://learnopencv.com/image-classification-pretrained-imagenet-models-tensorflow-keras/) - We will learn how to use pre-trained ImageNet models (pre-trained CNNs) to perform image classification. The ImageNet dataset contains 1,000 classes. - [Implementing a CNN in TensorFlow & Keras](https://learnopencv.com/implementing-cnn-tensorflow-keras/) - In this post, we will learn how to implement a Convolutional Neural Network (CNN) in Keras using a small dataset called CIFAR-10. - [Tensorflow & Keras Tutorial: Linear Regression](https://learnopencv.com/tensorflow-keras-tutorial-linear-regression/) - In this post, we will cover the fundamental components of a simple (linear) neural network in the context of linear regression. - [Understanding Feedforward Neural Networks](https://learnopencv.com/understanding-feedforward-neural-networks/) - In this article, we will learn about the concepts involved in feedforward Neural Networks in an intuitive and interactive way using tensorflow playground. - [Getting Started with Neural Networks: A 30,000-Foot View for Beginners](https://learnopencv.com/neural-networks-a-30000-feet-view-for-beginners/) - In this post, we provide a 30,000 feet view of Neural Networks. The post is for absolute beginners who are looking to get started with neural networks. - [Simple Background Estimation in Videos using OpenCV (C++/Python)](https://learnopencv.com/simple-background-estimation-in-videos-using-opencv-c-python/) - A tutorial for estimating the background in a static camera video feed with moving objects. - [Image Filtering Using Convolution in OpenCV](https://learnopencv.com/image-filtering-using-convolution-in-opencv/) - Learn about image filtering using OpenCV with various 2D-convolution kernels to blur and sharpen an image, in both Python and C++. - [FCOS- Anchor Free Object Detection Explained](https://learnopencv.com/fcos-anchor-free-object-detection-explained/) - FCOS - Get rid of hyperparameter tuning for anchors.FCOS is a great idea for making the object detection problem simpler and faster. - [FCOS- Anchor Free Object Detection Explained](https://learnopencv.com/fcos-anchor-free-object-detection-explained/) - FCOS - Get rid of hyperparameter tuning for anchors.FCOS is a great idea for making the object detection problem simpler and faster. - [Semantic Segmentation using KerasCV DeepLabv3+](https://learnopencv.com/kerascv-deeplabv3-plus-semantic-segmentation/) - Fine-tune KerasCV DeepLabv3+ model for semantic segmentation tasks and train it on the Satellite Images of Water Bodies dataset. Deeplabv3 - [YOLOX Object Detector Paper Explanation and Custom Training](https://learnopencv.com/yolox-object-detector-paper-explanation-and-custom-training/) - YOLOX object detector is a single-stage real-time detector. Check out detailed explanation of YOLOX paper and training YOLOX on custom data. YOLOX GitHub. - [YOLOR - Paper Explanation & Inference - An In-Depth Analysis](https://learnopencv.com/yolor-paper-explanation-inference-an-in-depth-analysis/) - YOLOR, inspired by how humans combine knowledge, is an object detection model that pushes the boundaries of real-time detection with improved speed & accuracy. - [PaddleOCR: Unveiling the Power of Optical Character Recognition](https://learnopencv.com/optical-character-recognition-using-paddleocr/) - PaddleOCR: Learn How to Recognize Text in Images Using Different OCR Algorithms from PaddleOCR and Understand Their Process. implement compare OCR algorithms - [PaddleOCR: Unveiling the Power of Optical Character Recognition](https://learnopencv.com/optical-character-recognition-using-paddleocr/) - PaddleOCR: Learn How to Recognize Text in Images Using Different OCR Algorithms from PaddleOCR and Understand Their Process. implement compare OCR algorithms - [PaddleOCR: Unveiling the Power of Optical Character Recognition](https://learnopencv.com/optical-character-recognition-using-paddleocr/) - PaddleOCR: Learn How to Recognize Text in Images Using Different OCR Algorithms from PaddleOCR and Understand Their Process. implement compare OCR algorithms - [Automatic Document Scanner using OpenCV](https://learnopencv.com/automatic-document-scanner-using-opencv/) - Learn how to create OpenCV Document Scanner using classical computer vision tools like Edge detection, Homography, Grabcut and deploy a streamlit web app. - [Automatic Document Scanner using OpenCV](https://learnopencv.com/automatic-document-scanner-using-opencv/) - Learn how to create OpenCV Document Scanner using classical computer vision tools like Edge detection, Homography, Grabcut and deploy a streamlit web app. - [Automatic Document Scanner using OpenCV](https://learnopencv.com/automatic-document-scanner-using-opencv/) - Learn how to create OpenCV Document Scanner using classical computer vision tools like Edge detection, Homography, Grabcut and deploy a streamlit web app. - [Automatic Document Scanner using OpenCV](https://learnopencv.com/automatic-document-scanner-using-opencv/) - Learn how to create OpenCV Document Scanner using classical computer vision tools like Edge detection, Homography, Grabcut and deploy a streamlit web app. - [Conditional GAN (cGAN) in PyTorch and TensorFlow](https://learnopencv.com/conditional-gan-cgan-in-pytorch-and-tensorflow/) - Conditional Generative Adversarial Network or CGAN - Generate Rock Paper Scissor images with Conditional GAN in PyTorch and TensorFlow implementation. - [DeepLabv3 & DeepLabv3+ The Ultimate PyTorch Guide](https://learnopencv.com/deeplabv3-ultimate-guide/) - DeepLabv3 & DeepLabv3+, developed by Google researchers, are semantic segmentation models that achieved SOTA performance on Pascal VOC and Cityscapes test sets. - [Live CV : A Computer Vision Coding Application](https://learnopencv.com/live-cv/) - Live computer vision coding application built using Qt and QML - [Human Pose Estimation using Keypoint RCNN in PyTorch](https://learnopencv.com/human-pose-estimation-using-keypoint-rcnn-in-pytorch/) - Human Pose Estimation is an important research area in the field of Computer Vision. It deals with estimating unique points on the human body, also called keypoints. In this blog post, we will discuss one such algorithm for finding keypoints on images containing a human called Keypoint-RCNN. The code is written in Pytorch, using the Torchvision library. - [Human Action Recognition using Detectron2 and LSTM](https://learnopencv.com/human-action-recognition-using-detectron2-and-lstm/) - Learn how to create a Human Action Recognition Application using PyTorch involving analyzing, predicting & classifying actions performed in that video. - [Principal Component Analysis](https://learnopencv.com/principal-component-analysis/) - Intuitively learn about Principal Component Analysis (PCA) without getting caught up in all the mathematical details. - [Face Reconstruction using EigenFaces (C++/Python)](https://learnopencv.com/face-reconstruction-using-eigenfaces-cpp-python/) - Tutorial (C++ / Python) for reconstructing a face using EigenFaces. You will also learn how to use Principal Component Analysis (PCA) on facial images. - [Enhancing Medical Multi-Label Image Classification Using PyTorch & Lightning](https://learnopencv.com/medical-multi-label/) - Medical diagnostics rely on quick, precise image classification. Using PyTorch & Lightning, we fine-tune EfficientNetv2 for medical multi-label classification. - [Stanford MRNet Challenge: Classifying Knee MRIs](https://learnopencv.com/stanford-mrnet-challenge-classifying-knee-mris/) - Stanford ML Group, led by Andrew Ng, works on important problems in areas such as healthcare and climate change, using AI. Last year they released a knee MRI dataset consisting of 1,370 knee MRI exams performed at Stanford University Medical Center. Subsequently, the MRNet challenge was also announced. For those wishing to enter the field - [Transfer Learning for Medical Images](https://learnopencv.com/transfer-learning-for-medical-images/) - Should we use ImageNet architectures and ImageNet pre-trained weights for medical image analysis? Learn from the latest research on the subject. - [Introduction to Epipolar Geometry and Stereo Vision](https://learnopencv.com/introduction-to-epipolar-geometry-and-stereo-vision/) - We will learn the concepts of Epipolar geometry and point correspondences. We will then use these concepts discuss how to calculate depth from stereo disparity. - [Depth Estimation Using Stereo Matching](https://learnopencv.com/depth-estimation-using-stereo-matching/) - Depth estimation is a critical task for autonomous driving. It's necessary to estimate the distance to cars, pedestrians, bicycles, animals, and obstacles.The popular way to estimate depth is LiDAR. However, the hardware price is high, LiDAR is sensitive to rain and snow, so there is a cheaper alternative: depth estimation with a stereo camera. This - [Duplicate Search on Quora Dataset](https://learnopencv.com/duplicate-search-on-quora-dataset/) - In this post we will use Universal Sentence Encoder from TensorflowHub to search for semantic duplicates in the Quora Dataset. - [Object Detection With Depth Measurement Using Pre-trained Models With OAK-D](https://learnopencv.com/object-detection-with-depth-measurement-with-oak-d/) - Tutorial on how to run pre-trained Neural network models from different model zoos with depth measurement on OAK using DepthAI - [YOLOv5: Expert Guide to Custom Object Detection Training](https://learnopencv.com/custom-object-detection-training-using-yolov5/) - YOLOv5 - In this article, we are fine-tuning small and medium models for custom object detection training and also carrying out inference using the trained models. - [YOLOv5: Expert Guide to Custom Object Detection Training](https://learnopencv.com/custom-object-detection-training-using-yolov5/) - YOLOv5 - In this article, we are fine-tuning small and medium models for custom object detection training and also carrying out inference using the trained models. - [YOLOv5: Expert Guide to Custom Object Detection Training](https://learnopencv.com/custom-object-detection-training-using-yolov5/) - YOLOv5 - In this article, we are fine-tuning small and medium models for custom object detection training and also carrying out inference using the trained models. - [YOLOv4 and Darknet For Pothole Detection](https://learnopencv.com/pothole-detection-using-yolov4-and-darknet/) - YOLOv4: We will train YOLOv4 (one-stage object detection model) on a custom pothole detection dataset using the Darknet framework and carry out inference. - [YOLOv3 - Deep Learning Based Object Detection - YOLOv3 with OpenCV ( Python / C++ )](https://learnopencv.com/deep-learning-based-object-detection-using-yolov3-with-opencv-python-c/) - YOLOV3 - Learn Object Detection using YOLOv3 with OpenCV, a super fast and as good as Single Shot MultiBox (SSD) method. C++/Python code provided for practice - [Face Recognition Models: Advancements, Toolkit, and Datasets](https://learnopencv.com/face-recognition-models/) - Face Recognition Models: Dive deepinto the realm of face recognition models such as DeepFace, FaceNet, VGG-Face, & ArcFace, toolkits, datasets, and pipelines. - [Facial Emotion Recognition: Decoding Expressions](https://learnopencv.com/facial-emotion-recognition/) - Facial Emotion Recognition System: Unlock the secrets of human emotions with bridging the gap between AI and empathy for deeper connections. - [Exploring SAHI: Slicing Aided Hyper Inference for Small Object Detection](https://learnopencv.com/slicing-aided-hyper-inference/) - Unveiling the secrets of small object detection, this groundbreaking research article introduces the revolutionary Slicing Aided Hyper Inference Technique. - [Fine-Tuning BERT using Hugging Face Transformers](https://learnopencv.com/fine-tuning-bert/) - Fine-Tuning BERT on Arxiv abstract classification dataset to recognize 11 types of abstract categories. using the Hugging Face Transformer library. - [SegFormer 🤗 : Fine-Tuning for Improved Lane Detection in Autonomous Vehicles](https://learnopencv.com/segformer-fine-tuning-for-lane-detection/) - SegFormerExplore the intricate fine-tuning pipeline of the HuggingFace SegFormer model, specifically for lane detection in autonomous vehicles. - [BERT: Bidirectional Encoder Representations from Transformers - Unlocking the Power of Deep Contextualized Word Embeddings](https://learnopencv.com/bert-bidirectional-encoder-representations-from-transformers/) - An introduction to BERT, short for Bidirectional Encoder Representations from Transformers including the model architecture, inference, and training. - [PaddlePaddle: Exploring Object Detection, Segmentation, and Keypoints](https://learnopencv.com/paddlepaddle/) - Unlock AI's power with PaddlePaddle, the go-to deep learning platform. Discover its innovative features and learn how it fuels robust machine learning models. - [Weighted Boxes Fusion in Object Detection: A Comparison with Non-Maximum Suppression](https://learnopencv.com/weighted-boxes-fusion/) - Weighted boxes Fusion excels as an effective and efficient post-processing step as compared to the traditional Non-Maximum Suppression in object detection. - [Medical Image Segmentation Using 🤗 HuggingFace & PyTorch](https://learnopencv.com/medical-image-segmentation/) - Medical Image Segmentation - Explore using the UW-Madison dataset, fine-tune Segformer with PyTorch & HuggingFace transformers, & deploy a Gradio inference app - [A Closer Look at CVAT: Perfecting Your Annotations](https://learnopencv.com/a-closer-look-at-cvat-perfecting-your-annotations/) - Explore the powerful capabilities of CVAT Annotation Tool, and learn how to streamline image and video labeling with its intuitive features and functionality. - [Top 5 AI papers of September 2023](https://learnopencv.com/top-5-ai-papers-of-september-2023/) - In this article, we go over the best AI papers of September 2023, which include Vision Transformers, GPT-4, LLMs, and making Vision Transformers more efficient. - [Autoencoders Explored: Understanding and Implementing Denoising Autoencoders with Tensorflow (Python)](https://learnopencv.com/understanding-autoencoders-using-tensorflow-python/) - Get to know autoencoders in Deep Learning! In this post, we make it easy to understand how to set up denoising autoencoders with Tensorflow-Python - [TrOCR - Getting Started with Transformer Based OCR](https://learnopencv.com/trocr-getting-started-with-transformer-based-ocr/) - In this article, we explore TrOCR architecture, models, training strategy and run inference using HuggingFace. We also analyze successful and failure cases. - [Generative Adversarial Networks (GANs) - An Introduction](https://learnopencv.com/introduction-to-generative-adversarial-networks/) - Generative Adversarial Networks GANS: Learn the theoretical concepts and their practical applications, and implement a vanilla GAN in Pytorch & Tensorflow. - [Build a Video to Slides Converter Application using the Power of Background Estimation and Frame Differencing in OpenCV](https://learnopencv.com/video-to-slides-converter-using-background-subtraction/) - This blog post aims to build a simple video to slides converter application using Frame Differencing and Background Modeling techniques using OpenCV - [Real Time Deep SORT with Torchvision Detectors](https://learnopencv.com/real-time-deep-sort-with-torchvision-detectors/) - Carry out object tracking and re-identification in videos using Deep SORT with Torchvision detectors, Torchreid, and OpenAI CLIP embedders. - [Top 5 AI papers of August 2023](https://learnopencv.com/top-5-ai-papers-of-august-2023/) - The post on the Top 5 AI Papers of August 2023 gives an excellent overview of all the latest trends happening in the LLM, CV, and AI space. - [Fine Tuning TrOCR - Training TrOCR to Recognize Curved Text](https://learnopencv.com/fine-tuning-trocr-training-trocr-to-recognize-curved-text/) - In this article, we are fine tuning TrOCR Small Printed model on the SCUT CTW1500 dataset to improve its performance on curved text. - [Object Tracking and Reidentification with FairMOT](https://learnopencv.com/object-tracking-and-reidentification-with-fairmot/) - Explaining and understanding the inner workings of FairMOT Tracker. Checkout the intermediate outputs, and compare the results with DeepSort Tracker - [Top 5 AI papers of July 2023](https://learnopencv.com/top-5-ai-papers-of-july-2023/) - Summary of top 5 AI papers of 2023 which include Llama 2, Flash Attention 2, Focus DETR, patch selectivity in ViTs, and LLM affecting education. - [Segment Anything - A Foundation Model for Image Segmentation](https://learnopencv.com/segment-anything/) - Explore Meta's Segment Anything model and dataset. This is a foundation model for image segmentation trained on 11 million images and 1.1 billion masks. - [IoU Loss Functions for Faster & More Accurate Object Detection](https://learnopencv.com/iou-loss-functions-object-detection/) - A compressive study of IoU loss functions for object detection loss function.A relative comparison of MSE, IoU, GIoU, DIoU, and CIoU loss function. - [Deploying a Deep Learning Model using Hugging Face Spaces and Gradio](https://learnopencv.com/deploy-deep-learning-model-huggingface-spaces/) - Deploying a deep learning model for pothole detection on images and videos using HuggingFace Spaces and Gradio. We use a custom YOLOv8 Nano for this. - [Top 10 AI Art Generation Tools using Diffusion Models](https://learnopencv.com/ai-art-generation-tools/) - AI Art Generation Tools that use Diffusion models either to generate art or allow us to search images that have been generated using AI are the new hype now. - [Driver Drowsiness Detection Using Mediapipe In Python](https://learnopencv.com/driver-drowsiness-detection-using-mediapipe-in-python/) - Driver drowsiness detection systems help reduce mishaps due to tired or sleepy drivers. Learn to build such a robust system using MediaPipe in Python. - [NVIDIA Spring GTC 2023 Day 2: Jensen’s keynote & the iPhone moment of AI is here!](https://learnopencv.com/nvidia-spring-gtc-2023-day-2-jensens-keynote-the-iphone-moment-of-ai-is-here/) - NVIDIA Spring GTC 2023 Day 2 starts with Jensen's keynote covering the latest in Quantum computing, Cloud Computing, inference using TensorRT & Triton. - [NVIDIA Spring GTC 2023 Day 4: Ending on a High Note with Top Moments from the Finale!](https://learnopencv.com/nvidia-spring-gtc-2023-day-4/) - NVIDIA Spring GTC 2023 Day 4 highlights are are here. Covering Ray Tracing and AI in Unreal Engine, features in CUDA C++, and Prallelism in PyTorch. - [Introduction to OpenVINO Deep Learning Workbench](https://learnopencv.com/introduction-to-openvino-deep-learning-workbench/) - OpenVINO Deep Learning Workbench is a Web-based application that does Model Optimization, Calibration, Quantization, and final Model deployment-ready faster. - [Running OpenVINO Models on Intel Integrated GPU](https://learnopencv.com/running-openvino-models-on-intel-integrated-gpu/) - Learn how to run OpenVINO models on Intel Integrated GPU. From installing proper Intel GPU drivers to running the FP16 deep learning models on the Intel GPU. - [Post Training Quantization with OpenVINO Toolkit](https://learnopencv.com/post-training-quantization-with-openvino-toolkit/) - Post Training Quantization can be done using the Intel OpenVINO Toolkit which allows us to reduce model size by reducing the weights from FP32 to INT. - [NVIDIA Spring GTC 2023 Day 3: Digging deeper into Deep Learning, Semiconductors & more!](https://learnopencv.com/nvidia-spring-gtc-2023-day-3-digging-deeper-into-deep-learning-semiconductors-more/) - In this article, we take a look at all the interesting things that happened at NVIDIA Spring GTC 2023 Day 3. - [NVIDIA Spring GTC 2023 Day 1: Welcome to the future!](https://learnopencv.com/nvidia-spring-gtc-2023-day-1-highlights-welcome-to-the-future/) - NVIDIA Spring GTC 2023 Day 1 highlights give an overview of all the interesting and important that happened throughout GTC 2023 Day 1. - [NVIDIA GTC Spring 2023 Curtain Raiser](https://learnopencv.com/nvidia-gtc-spring-2023-curtain-raiser/) - NVIDIA GTC Spring 2023 Edition is back with all the latest advancements in Artificial Intelligence, High-Performance Computing, and Industry Leading Software. - [OpenCV Face Recognition - Does Face Recognition Work on AI-Generated Images?](https://learnopencv.com/opencv-face-recognition-api/) - Can facial recognition technology work on AI-generated faces? We explore this with OpenCV Face Recognition. Find out the results in our blog post. - [Mastering DALL·E 2: A Breakthrough in AI Art Generation](https://learnopencv.com/mastering-dall-e-2/) - Discover the remarkable capabilities of DALL·E 2, OpenAI's generative deep learning model that creates stunningly realistic and diverse images from text prompts - [Deep Convolutional GAN -DCGAN - in PyTorch and TensorFlow](https://learnopencv.com/deep-convolutional-gan-in-pytorch-and-tensorflow/) - Learn the theoretical concepts of Deep Convolutional GAN. Code DCGAN in both PyTorch GAN & TensorFlow GAN frameworks on Anime Faces Dataset. - [Create Snapchat/Instagram Filters Using Mediapipe](https://learnopencv.com/create-snapchat-instagram-filters-using-mediapipe/) - A tutorial for using Mediapipe’s Face-Mesh to create Augmented Reality Facial Filters. We are sharing the code in Python. - [Fully Convolutional Network For Image Classification on Arbitrary Sized Image](https://learnopencv.com/fully-convolutional-image-classification-on-arbitrary-sized-image/) - Fully Convolutional Network for Image Classification on arbitrary sized images without using the computationally expensive sliding window approach- Pytorch code - [Understanding Attention Mechanism in Transformer Neural Networks](https://learnopencv.com/attention-mechanism-in-transformer-neural-networks/) - Intuitively understanding the self attention mechanism in 4 simple steps, followed by mathematical understanding & finally implementing it in PyTorch. - [Center Stage for Zoom Calls Using MediaPipe](https://learnopencv.com/center-stage-for-zoom-calls-using-mediapipe/) - Canter stage zoom: We implement the Center Stage Technology of Apple in a Zoom call using OpenCv & Mediapipe. Use MediaPipe & Video Stabiliser for face tracking - [Mediapipe Gesture Recognition - Gesture Control in Zoom Call](https://learnopencv.com/gesture-control-in-zoom-call-using-mediapipe/) - Mediapipe Gesture Recognition - Track hand gestures & convert them to actions like zooming in, blurring background & switching the camera On/Off via MediaPipe. - [Deep learning based Object Detection and Instance Segmentation using Mask RCNN in OpenCV (Python / C++)](https://learnopencv.com/deep-learning-based-object-detection-and-instance-segmentation-using-mask-rcnn-in-opencv-python-c/) - Learn object detection and instance segmentation using Mask RCNN in OpenCV (a region based ConvNet). Code in Python and C++ is provided for study and practice. - [Batch Normalization in Deep Networks](https://learnopencv.com/batch-normalization-in-deep-networks/) - In this post, we will learn what Batch Normalization is, why it is needed, how it works, and how to implement it using Keras. - [How To Select a Bounding Box in OpenCV Region Of Interest - ROI (C++/Python)?](https://learnopencv.com/how-to-select-a-bounding-box-roi-in-opencv-cpp-python/) - A tutorial on how to select one or more bounding boxes in OpenCV. Bounding box in OpenCV on an image (region of interest) - C++/Python - [How to Convert a Model from PyTorch to TensorRT and Speed Up Inference](https://learnopencv.com/how-to-convert-a-model-from-pytorch-to-tensorrt-and-speed-up-inference/) - Learn how to convert a PyTorch to TensorRT to speed up inference. We provide step by step instructions with code. - [Deep Learning Based Text Detection Using OpenCV (C++/Python)](https://learnopencv.com/deep-learning-based-text-detection-using-opencv-c-python/) - Deep Learning Text Detection using OpenCV. The post is not only about detecting the text in an image but also about what is written in the text. - [Image Segmentation Using Computer Vision](https://learnopencv.com/image-segmentation/) - A closer look at the definitions of Image Segmentation, Semantic Segmentation, Instance Segmentation, and Panoptic Segmentation. - [Face Recognition - Introduction for Beginners - Nearly Everything You Need to Know](https://learnopencv.com/face-recognition-an-introduction-for-beginners/) - Face Recognition is a computer vision technique which enables a computer to predict the identity of a person from an image. This is a multi-part series on face recognition. This post will give us a 30,000 feet view of how face recognition works. We will not go into the details of any particular algorithm but - [Face Recognition with ArcFace](https://learnopencv.com/face-recognition-with-arcface/) - Introduction to Face Recognition with Arcface concepts through the use of ArcFace loss. - [Anti Spoofing Face Recognition System using OAK-D and DepthAI](https://learnopencv.com/anti-spoofing-face-recognition-system-using-oak-d-and-depthai/) - Anti spoofing face recognition - Pros & cons of using Face Recognition as an authentication method and how it can be spoofed &how to detect the spoofing attempt - [TensorFlow Lite Model Maker: Create Models for On-Device Machine Learning](https://learnopencv.com/tensorflow-lite-model-maker-create-models-for-on-device-machine-learning/) - TensorFlow Lite Model - Create a TensorFlow Lite model using the TF Lite Model Maker Library different model optimization techniques - TF Lite series - [TensorFlow Lite: TFLite Model Optimization for On-Device Machine Learning](https://learnopencv.com/tensorflow-lite-model-optimization-for-on-device-machine-learning/) - Tflite Model Optimization - The 1st post of the TF Lite series provides an introduction to TF Lite and discusses different model optimization techniques - [TensorFlow Model Optimization Toolkit - A Deep Dive](https://learnopencv.com/deep-dive-into-tensorflow-model-optimization-toolkit/) - TensorFlow Model Optimization - A thorough analysis of different model optimization techniques supported by the TensorFlow Model Optimization Toolkit (TF MOT) - [Activation Functions in Deep Learning - A Complete Overview](https://learnopencv.com/understanding-activation-functions-in-deep-learning/) - Activation Functions in Deep Learning are a key part of neural network design. Learn about Sigmoid, tanh, ReLU, Leaky ReLU, Parametric ReLU & SWISH - [CNN Fully Convolutional Image Classification (FCN CNN) with TensorFlow -](https://learnopencv.com/cnn-fully-convolutional-image-classification-with-tensorflow/) - FCN CNN - We explore the concept of fully convolutional neural networks in TensorFlow to show how to solve the classification task using the input image of arbitrary size. - [EfficientNet: Theory + Code](https://learnopencv.com/efficientnet-theory-code/) - Efficientnet - [DepthAI Pipeline Overview: Creating a Complex Pipeline](https://learnopencv.com/depthai-pipeline-overview-creating-a-complex-pipeline/) - This post provides us with an overview of different nodes that are available to us in the DepthAI API and how they work together to form a working pipeline. - [t-SNE: T-Distributed Stochastic Neighbor Embedding Explained](https://learnopencv.com/t-sne-t-distributed-stochastic-neighbor-embedding-explained/) - t-SNE (t-Distributed Stochastic Neighbor Embedding) is a dimensionality reduction techniques used to vizualize data. Continue reading to know more. - [t-SNE: T-Distributed Stochastic Neighbor Embedding Explained](https://learnopencv.com/t-sne-t-distributed-stochastic-neighbor-embedding-explained/) - t-SNE (t-Distributed Stochastic Neighbor Embedding) is a dimensionality reduction techniques used to vizualize data. Continue reading to know more. - [GOTURN : Deep Learning based Object Tracking](https://learnopencv.com/goturn-deep-learning-based-object-tracking/) - A tutorial for GOTURN : A Deep Learning based object tracking algorithm. We share code in C++ and Python using OpenCV's Tracking API. - [MultiTracker : Multiple Object Tracking using OpenCV (C++/Python)](https://learnopencv.com/multitracker-multiple-object-tracking-using-opencv-c-python/) - A (C++/Python) tutorial for OpenCV's multi-object tracking API (MultiTracker) implemented using the MultiTracker class. - [Understanding Multiple Object Tracking using DeepSORT](https://learnopencv.com/understanding-multiple-object-tracking-using-deepsort/) - Get an overview of Tracking, the different types of object trackers, how tracking works, and what evaluation metrics are used to measure their performance. - [Understanding Multiple Object Tracking using DeepSORT](https://learnopencv.com/understanding-multiple-object-tracking-using-deepsort/) - Get an overview of Tracking, the different types of object trackers, how tracking works, and what evaluation metrics are used to measure their performance. - [Understanding Multiple Object Tracking using DeepSORT](https://learnopencv.com/understanding-multiple-object-tracking-using-deepsort/) - Get an overview of Tracking, the different types of object trackers, how tracking works, and what evaluation metrics are used to measure their performance. - [TensorBoard with PyTorch Lightning](https://learnopencv.com/tensorboard-with-pytorch-lightning/) - Through this blog, we will learn how can TensorBoard be used along with PyTorch Lightning to make development easy with beautiful and interactive visualizations - [Alpha Blending Using OpenCV (C++ / Python)](https://learnopencv.com/alpha-blending-using-opencv-cpp-python/) - Alpha blending using OpenCV - We'll learn how to alpha blend two images and overlay a transparent PNG image over another image with code in both C++ and Python - [t-SNE for Feature Visualization](https://learnopencv.com/t-sne-for-feature-visualization/) - In Machine Learning, we always want to get insights into data: like getting familiar with the training samples or better understanding the label distribution. To do that, we visualize the data in many different ways. Typically, we need to look into multiple characteristics of the data simultaneously. In classic ML, for example, the data may - [Best Project Award : Computer Vision for Faces](https://learnopencv.com/best-project-award-computer-vision-for-faces/) - The first batch of our course on Computer Vision for Faces has graduated and I am very excited to announce the Best Project Award for our course. It has a cash prize of 00. But, the journey people went through, was priceless! The response to the course was overwhelming. 429 students signed up for the - [CV4Faces : Best Project Award 2018](https://learnopencv.com/cv4faces-best-project-award-2018/) - It gives me immense pleasure to announce the best project award for our online course "Computer Vision for Faces" (cv4faces). These awards are given out twice a year to the top three projects submitted by students enrolled in cv4faces. You can check out the winners of last year's best project award here. We launched cv4faces - [Katharsis : A Software Engineer's first steps in Computer Vision and Machine Learning](https://learnopencv.com/katharsis-software-engineers-first-step-in-cvml/) - This post describes the experience of Santhosh, a Bengaluru based Software Engineer in Computer Vision for Faces 2018 course. - [CV4Faces : Best Project Award Fall 2018](https://learnopencv.com/cv4faces-best-project-award-fall-2018/) - Computer Vision for Faces best project award. First prize: Coin Identification and Counting. Second Prize: Face Clustering and Recognition on Youtube videos. Third Prize: Face Swap. - [Hangman: Creating games in OpenCV](https://learnopencv.com/hangman-creating-games-in-opencv/) - In this post we will see how to develop the Hangman game using the basics of OpenCV and Pandas library in Python. - [Kickstarter: AI Courses by OpenCV.org](https://learnopencv.com/kickstarter-ai-courses-by-opencv-org/) - OpenCV.org is launching a Kickstarter campaign in May 2019 to create 3 Computer Vision courses. - [GTC 2022 Big Bang AI announcements: Everything you need to know](https://learnopencv.com/gtc-2022-big-bang-ai-announcements-everything-you-need-to-know/) - GTC'22 has lots of new announcements with improvements across hardware & software, NVIDIA is driving several industries towards autonomy, safety & reliability. - [NVIDIA GTC 2022 : The most important AI event this Fall](https://learnopencv.com/nvidia-gtc-2022-the-most-important-ai-event-this-fall/) - In Today's GTC 2022 post, we have shared how experts and industry leaders in industrial AI got started and traced their rewarding career journeys to the top. - [NVIDIA GTC 2022 : The most important AI event this Fall](https://learnopencv.com/nvidia-gtc-2022-the-most-important-ai-event-this-fall/) - In Today's GTC 2022 post, we have shared how experts and industry leaders in industrial AI got started and traced their rewarding career journeys to the top. - [NVIDIA GTC 2022 : The most important AI event this Fall](https://learnopencv.com/nvidia-gtc-2022-the-most-important-ai-event-this-fall/) - In Today's GTC 2022 post, we have shared how experts and industry leaders in industrial AI got started and traced their rewarding career journeys to the top. - [NVIDIA GTC 2022 : The most important AI event this Fall](https://learnopencv.com/nvidia-gtc-2022-the-most-important-ai-event-this-fall/) - In Today's GTC 2022 post, we have shared how experts and industry leaders in industrial AI got started and traced their rewarding career journeys to the top. - [NVIDIA GTC 2022 : The most important AI event this Fall](https://learnopencv.com/nvidia-gtc-2022-the-most-important-ai-event-this-fall/) - In Today's GTC 2022 post, we have shared how experts and industry leaders in industrial AI got started and traced their rewarding career journeys to the top. - [NVIDIA GTC 2022 : The most important AI event this Fall](https://learnopencv.com/nvidia-gtc-2022-the-most-important-ai-event-this-fall/) - In Today's GTC 2022 post, we have shared how experts and industry leaders in industrial AI got started and traced their rewarding career journeys to the top. - [NVIDIA GTC 2022 Day 1 Highlights: Brilliant Start](https://learnopencv.com/gtc-day-1-highlights/) - This post brings you NVIDIA GTC Day 1 Highlights First day had sessions on topics from physics simulation to anomaly detection cybersecurity & 3D deep learning - [NVIDIA GTC 2022 Day 1 Highlights: Brilliant Start](https://learnopencv.com/gtc-day-1-highlights/) - This post brings you NVIDIA GTC Day 1 Highlights First day had sessions on topics from physics simulation to anomaly detection cybersecurity & 3D deep learning - [NVIDIA GTC 2022 Day 1 Highlights: Brilliant Start](https://learnopencv.com/gtc-day-1-highlights/) - This post brings you NVIDIA GTC Day 1 Highlights First day had sessions on topics from physics simulation to anomaly detection cybersecurity & 3D deep learning - [NVIDIA GTC 2022 Day 1 Highlights: Brilliant Start](https://learnopencv.com/gtc-day-1-highlights/) - This post brings you NVIDIA GTC Day 1 Highlights First day had sessions on topics from physics simulation to anomaly detection cybersecurity & 3D deep learning - [NVIDIA GTC 2022 Day 1 Highlights: Brilliant Start](https://learnopencv.com/gtc-day-1-highlights/) - This post brings you NVIDIA GTC Day 1 Highlights First day had sessions on topics from physics simulation to anomaly detection cybersecurity & 3D deep learning - [NVIDIA GTC 2022 Day 1 Highlights: Brilliant Start](https://learnopencv.com/gtc-day-1-highlights/) - This post brings you NVIDIA GTC Day 1 Highlights First day had sessions on topics from physics simulation to anomaly detection cybersecurity & 3D deep learning - [NVIDIA GTC 2022 Day 1 Highlights: Brilliant Start](https://learnopencv.com/gtc-day-1-highlights/) - This post brings you NVIDIA GTC Day 1 Highlights First day had sessions on topics from physics simulation to anomaly detection cybersecurity & 3D deep learning - [NVIDIA GTC 2022 Day 4 Highlights: Meet the new Jetson Orin](https://learnopencv.com/nvidia-gtc-2022-day-4-highlights-meet-the-new-jetson-orin/) - Supercomputer on wheels: Learn about Jetson Orin, NVIDIA’s latest edge computer for autonomous robots also read about agricultural robots, drones, robotic arms - [NVIDIA GTC 2022 Day 3 Highlights: Deep Dive into Hopper architecture](https://learnopencv.com/nvidia-gtc-2022-day-3-highlights-deep-dive-into-hopper-architecture/) - This blogpost shares details of the AI specific enhancements in the latest Hopper architecture by NVIDIA, advice by Andrew Ng on data centric AI and many more - [NVIDIA GTC 2022 Day 2 Highlights: Jensen's Keynote](https://learnopencv.com/nvidia-gtc-2022-day-2-highlights/) - Day 2 coverage of the NVIDIA GTC conference includes topics like Jensen’s keynote, Hopper H100 GPU, Building a career in AI, and more. - [NVIDIA GTC 2022 Day 2 Highlights: Jensen's Keynote](https://learnopencv.com/nvidia-gtc-2022-day-2-highlights/) - Day 2 coverage of the NVIDIA GTC conference includes topics like Jensen’s keynote, Hopper H100 GPU, Building a career in AI, and more. - [NVIDIA GTC 2022 Day 2 Highlights: Jensen's Keynote](https://learnopencv.com/nvidia-gtc-2022-day-2-highlights/) - Day 2 coverage of the NVIDIA GTC conference includes topics like Jensen’s keynote, Hopper H100 GPU, Building a career in AI, and more. - [NVIDIA GTC 2022 Day 2 Highlights: Jensen's Keynote](https://learnopencv.com/nvidia-gtc-2022-day-2-highlights/) - Day 2 coverage of the NVIDIA GTC conference includes topics like Jensen’s keynote, Hopper H100 GPU, Building a career in AI, and more. - [NVIDIA GTC 2022 Day 2 Highlights: Jensen's Keynote](https://learnopencv.com/nvidia-gtc-2022-day-2-highlights/) - Day 2 coverage of the NVIDIA GTC conference includes topics like Jensen’s keynote, Hopper H100 GPU, Building a career in AI, and more. - [How to use OpenCV DNN Module with NVIDIA GPUs on Linux](https://learnopencv.com/opencv-dnn-with-gpu-support/) - Learn compiling the OpenCV library with DNN GPU support to speed up the neural network inference. We will discuss how to use OpenCV DNN Module with NVIDIA GPUs. - [Plastic Waste Detection with Deep Learning](https://learnopencv.com/plastic-waste-detection-with-deep-learning/) - Learn how to use computer vision to tackle the waste management problem and also the tools that helps to make the process much faster. - [Demystifying GPU Architectures For Deep Learning: Part 2](https://learnopencv.com/demystifying-gpu-architectures-for-deep-learning-part-2/) - Discover the different types of NVIDIA GPU architectures likes Ampere, Turing and Hopper. Learn how using cuDNN maximizes GPU efficiency. - [Demystifying GPU Architectures For Deep Learning - Part 1](https://learnopencv.com/demystifying-gpu-architectures-for-deep-learning/) - Introducing GPU architecture to deep learning practitioners. We dive deep into the CUDA programming model and implement a dense layer in CUDA. - [Ensemble Deep Learning-based Defect Classification and Detection in SEM Images](https://learnopencv.com/ensemble-deep-learning-based-defect-classification-and-detection-in-sem-images/) - Today’s post will teach how computer vision impacts the semiconductor industry with a specific example of defect detection and classification. - [Multi-Attribute and Graph-based Object Detection](https://learnopencv.com/multi-attribute-and-graph-based-object-detection/) - A step by step guide and code for using multiple attributes and graphs to detect complex objects along with detailed examples. - [Top 10 Sources to Find Computer Vision and AI Models](https://learnopencv.com/top-10-sources-to-find-computer-vision-and-ai-models/) - In this post, we will look at the list of popular sources where you can find different Deep Learning Models to jump-start your Machine Learning application. - [Top 10 Sources to Find Computer Vision and AI Models](https://learnopencv.com/top-10-sources-to-find-computer-vision-and-ai-models/) - In this post, we will look at the list of popular sources where you can find different Deep Learning Models to jump-start your Machine Learning application. - [AUTOSAR C++ compliant deep learning inference with TensorRT](https://learnopencv.com/autosar-c-compliant-deep-learning-inference-with-tensorrt/) - In this post, we show how to deploy a deep neural network in safety critical applications where bugs can endanger human lives - [Model Selection and Benchmarking with Modelplace.AI](https://learnopencv.com/model-selection-and-benchmarking-with-modelplace-ai/) - Learn how to select the right model using Modelplace.AI to make your application faster, scale it to millions of requests, and cut down cloud computing costs. - [Model Selection and Benchmarking with Modelplace.AI](https://learnopencv.com/model-selection-and-benchmarking-with-modelplace-ai/) - Learn how to select the right model using Modelplace.AI to make your application faster, scale it to millions of requests, and cut down cloud computing costs. - [Building Industrial embedded deep learning inference pipelines with TensorRT](https://learnopencv.com/building-industrial-embedded-deep-learning-inference-pipelines-with-tensorrt/) - You can scarcely find a good article on deploying computer vision systems in industrial scenarios. So, we decided to write a blog post series on the topic. The topics we will cover in this series are: Part 1: Building industrial embedded deep learning inference pipelines with TensorRT in python Part 2: Building industrial embedded deep - [Pose Detection comparison : wrnchAI vs OpenPose](https://learnopencv.com/pose-detection-comparison-wrnchai-vs-openpose/) - We compare the performance of Human Body Pose Estimation systems - wrnchAI and OpenPose. We evaluate both systems on various factors such as Speed, Accuracy etc - [Zero-shot Learning : An Introduction](https://learnopencv.com/zero-shot-learning-an-introduction/) - Deep learning based models have achieved the state of the art performance for image recognition and object detection tasks in the recent past. Many of these models are able to achieve human level performance on complex image classification datasets like ImageNet which includes a thousand diverse object classes. However, these models rely on supervised training - [AI behind the Diwali 2021 ‘Not just a Cadbury ad’](https://learnopencv.com/ai-behind-the-diwali-2021-not-just-a-cadbury-ad/) - Learn how Cadbury in partnership with Rephrase.ai utilized machine learning to synthesize video for each business owner with the voice of Shah Rukh Khan. - [Invisibility Cloak using simple CV techniques in OpenCV](https://learnopencv.com/invisibility-cloak-using-color-detection-and-segmentation-with-opencv/) - Tutorial on creating an invisibility cloak using OpenCV. Also learn color based segmentation. C++ and Python code is also provided for practice and study. - [Variational Autoencoder in TensorFlow](https://learnopencv.com/variational-autoencoder-in-tensorflow/) - Learn about Variational Autoencoder in TensorFlow. Implement VAE in TensorFlow on Fashion-MNIST and Cartoon Dataset. Compare latent space of VAE and AE. - [Real-time style transfer in a Zoom meeting](https://learnopencv.com/real-time-style-transfer-in-a-zoom-meeting/) - Learn to train your own fast style transfer network in PyTorch and deploy to get a live style transfer effect on zoom/Skype/ Microsoft Teams or Hangouts. - [Autoencoder in TensorFlow 2: Beginner's Guide](https://learnopencv.com/autoencoder-in-tensorflow-2-beginners-guide/) - Introduction to Autoencoder in TensorFlow, v2.4. Implement Autoencoder on Fashion-MNIST and Cartoon Dataset. Perform experiments with Autoencoder's latent-space - [Generative and Discriminative Models](https://learnopencv.com/generative-and-discriminative-models/) - Most of the Machine Learning and Deep Learning problems that you solve are conceptualized from the Generative and Discriminative Models. In Machine Learning, one can clearly distinguish between the two modelling types: Classifying an image as a dog or a cat falls under Discriminative Modelling Producing a realistic dog or a cat image is a - [Generative and Discriminative Models](https://learnopencv.com/generative-and-discriminative-models/) - Most of the Machine Learning and Deep Learning problems that you solve are conceptualized from the Generative and Discriminative Models. In Machine Learning, one can clearly distinguish between the two modelling types: Classifying an image as a dog or a cat falls under Discriminative Modelling Producing a realistic dog or a cat image is a - [Generative and Discriminative Models](https://learnopencv.com/generative-and-discriminative-models/) - Most of the Machine Learning and Deep Learning problems that you solve are conceptualized from the Generative and Discriminative Models. In Machine Learning, one can clearly distinguish between the two modelling types: Classifying an image as a dog or a cat falls under Discriminative Modelling Producing a realistic dog or a cat image is a - [Generative and Discriminative Models](https://learnopencv.com/generative-and-discriminative-models/) - Most of the Machine Learning and Deep Learning problems that you solve are conceptualized from the Generative and Discriminative Models. In Machine Learning, one can clearly distinguish between the two modelling types: Classifying an image as a dog or a cat falls under Discriminative Modelling Producing a realistic dog or a cat image is a - [Generative and Discriminative Models](https://learnopencv.com/generative-and-discriminative-models/) - Most of the Machine Learning and Deep Learning problems that you solve are conceptualized from the Generative and Discriminative Models. In Machine Learning, one can clearly distinguish between the two modelling types: Classifying an image as a dog or a cat falls under Discriminative Modelling Producing a realistic dog or a cat image is a - [MRNet - The Multi-Task Approach](https://learnopencv.com/mrnet-multitask-approach/) - Our last post on the MRNet challenge presented a simple way to approach it. There you learned to make a separate model for each disease. And ended up with three models. Time to up your game! Now combine all the three models into one and train it. This blog takes on from where the last - [Non Maximum Suppression: Theory and Implementation in PyTorch](https://learnopencv.com/non-maximum-suppression-theory-and-implementation-in-pytorch/) - Non Maximum Suppression (NMS) is a technique used in numerous computer vision tasks. It is a class of algorithms to select one entity (e.g., bounding boxes) out of many overlapping entities. We will discuss how to implement NMS using PyTorch - [Photoshop Filters in OpenCV](https://learnopencv.com/photoshop-filters-in-opencv/) - Learn to implement image editing filters in OpenCV. Add features like embossing, use filters like 60's TV and duo-tone, change brightness, and more. - [Classification with Localization: Convert any Keras Classifier to a Detector](https://learnopencv.com/classification-with-localization/) - Image classification is used to solve several Computer Vision problems; right from medical diagnoses, to surveillance systems, on to monitoring agricultural farms. There are innumerable possibilities to explore using Image Classification. If you have completed the basic courses on Computer Vision, you are familiar with the tasks and routines involved in Image Classification tasks. Want - [Making A Low-Cost Stereo Camera Using OpenCV](https://learnopencv.com/making-a-low-cost-stereo-camera-using-opencv/) - In this post, we will learn how to create a custom low-cost stereo camera (using a pair of webcams ) and capture 3D videos with it using OpenCV. We provide code in Python and C++. - [Making A Low-Cost Stereo Camera Using OpenCV](https://learnopencv.com/making-a-low-cost-stereo-camera-using-opencv/) - In this post, we will learn how to create a custom low-cost stereo camera (using a pair of webcams ) and capture 3D videos with it using OpenCV. We provide code in Python and C++. - [RAFT: Optical Flow estimation using Deep Learning](https://learnopencv.com/optical-flow-using-deep-learning-raft/) - In this post, we will discuss about two Deep Learning based approaches for motion estimation using Optical Flow. FlowNet is the first CNN approach for calculating Optical Flow and RAFT which is the current state-of-the-art method for estimating Optical Flow - [Background Subtraction with OpenCV and BGS Libraries](https://learnopencv.com/background-subtraction-with-opencv-and-bgs-libraries/) - In this post, you will learn how to apply Background Subtraction with OpenCV and BGS Libraries - [How to use OpenCV DNN Module with Nvidia GPU on Windows](https://learnopencv.com/how-to-use-opencv-dnn-module-with-nvidia-gpu-on-windows/) - Learn how to install and use OpenCV DNN Module with Nvidia GPU on Windows OS. The changes made to the module allow the use of Nvidia GPUs to speed up inference. - [Introduction to Video Classification and Human Activity Recognition](https://learnopencv.com/introduction-to-video-classification-and-human-activity-recognition/) - Learn video classification and human activity recognition - video classification methods and associated problems. Finally, make a video classifier using Keras. - [Improving Illumination in Night Time Images](https://learnopencv.com/improving-illumination-in-night-time-images/) - Improving Illumination in Night Time Images using OpenCV. Improve illumination in single images using bright/dark channel priors and transmission maps. - [Training a Custom Object Detector with DLIB & Making Gesture Controlled Applications](https://learnopencv.com/training-a-custom-object-detector-with-dlib-making-gesture-controlled-applications/) - In this post, we are going to learn how to train a custom (HOG + SVM) hand detector with dlib and then how to make gesture-controlled applications with it. - [Applications of Foreground-Background separation with Semantic Segmentation](https://learnopencv.com/applications-of-foreground-background-separation-with-semantic-segmentation/) - Using Semantic Segmentation and DeepLab V3 in PyTorch for background removal, background changing, background blurring, and creating an image filter. - [Seamless Cloning using OpenCV ( Python , C++ )](https://learnopencv.com/seamless-cloning-using-opencv-python-cpp/) - This tutorial explains Seamless Cloning using OpenCV by showing an image and video example. C++ and Python code included. - [Computer Vision for Predicting Facial Attractiveness](https://learnopencv.com/computer-vision-for-predicting-facial-attractiveness/) - A computer vision and machine learning tutorial for predicting facial attractiveness of a person from a single image - [Configuring Qt for OpenCV on OSX](https://learnopencv.com/configuring-qt-for-opencv-on-osx/) - This tutorial shows how to configure a Qt application to use OpenCV based on pkg-config - [Handwritten Digits Classification : An OpenCV ( C++ / Python ) Tutorial](https://learnopencv.com/handwritten-digits-classification-an-opencv-c-python-tutorial/) - Image classification tutorial and code (c++/python) using OpenCV. The HOG descriptor and SVM classifier usage is explained in detail. - [Automatic Red Eye Remover using OpenCV (C++ / Python)](https://learnopencv.com/automatic-red-eye-remover-using-opencv-cpp-python/) - Learn how to automatically remove red-eyes from digital photographs using OpenCV. We have shared code in both C++ and Python. - [cvui: A GUI lib built on top of OpenCV drawing primitives](https://learnopencv.com/cvui-gui-lib-built-on-top-of-opencv-drawing-primitives/) - In this tutorial we discuss the usage of cvui - a GUI lib built on top of OpenCV drawing primitives. - [SVM using Scikit-Learn in Python](https://learnopencv.com/svm-using-scikit-learn-in-python/) - This post explains the implementation of Support Vector Machines (SVMs) using Scikit-Learn library in Python. - [Multi Person Pose Estimation in OpenCV using OpenPose](https://learnopencv.com/multi-person-pose-estimation-in-opencv-using-openpose/) - In this tutorial, we will discuss how to use OpenPose model trained on COCO keypoints dataset to perform multi person Pose Estimation using OpenCV DNN module. - [Install OpenCV 3.4.4 on Windows (C++ and Python)](https://learnopencv.com/install-opencv-3-4-4-on-windows/) - In this post, we will provide a batch script for installing OpenCV 3.4.4 (C++ and Python 3) on Windows. - [Install OpenCV 3.4.4 on macOS (C++ and Python)](https://learnopencv.com/install-opencv-3-4-4-on-macos/) - In this post we will provide a bash script for installing OpenCV 3.4.4 on macOS Mojave and High Sierra - [Install OpenCV 4 on CentOS 7 (C++ and Python)](https://learnopencv.com/install-opencv-4-on-centos-7/) - In this post we will provide a bash script for installing OpenCV 4.0 on CentOS 7 - [Multi-Label Image Classification with PyTorch](https://learnopencv.com/multi-label-image-classification-with-pytorch/) - Tutorial for training a Convolutional Neural Network model for labeling an image with multiple classes. We are sharing code in PyTorch. - [Federated Learning using PyTorch and PySyft](https://learnopencv.com/federated-learning-using-pytorch-and-pysyft/) - A gentle introduction to federated learning using PyTorch and PySyft with the help of a real life example. - [Efficient image loading](https://learnopencv.com/efficient-image-loading/) - Comparison of different image loading methods to achieve the best performance. - [Playing Rock, Paper, Scissors with AI](https://learnopencv.com/playing-rock-paper-scissors-with-ai/) - In this post, you will learn how to train a robust rock, paper, scissor classifier, and then use it to make a full-fledged game that you can play with. - [Using Facial Landmarks for Overlaying Faces with Masks](https://learnopencv.com/using-facial-landmarks-for-overlaying-faces-with-masks/) - Learn how to overlay your face captured through a camera, with a virtual medical mask using facial landmarks. Have some fun trying out different masks yourself. - [Bag of Tricks for Image Classification](https://learnopencv.com/bag-of-tricks-for-image-classification/) - In this post, we are going to train a ResNet-18 Network with a bag of tricks to check the boost it gives. - [PyTorch to Tensorflow Model Conversion](https://learnopencv.com/pytorch-to-tensorflow-model-conversion/) - In this post, we will learn how to convert a PyTorch model to TensorFlow. If you are new to Deep Learning you may be overwhelmed by which framework to use. We personally think PyTorch is the first framework you should learn, but it may not be the only framework you may want to learn. The - [Image Classification with OpenCV for Android](https://learnopencv.com/image-classification-with-opencv-for-android/) - In the previous post, we've learned how to work with OpenCV Java API with the example of a PyTorch convolutional neural network, integrated into the Java pipeline. Now we are going to transform the obtained experience into a lightweight Android application. There are some challenges on the way of creating such an application, and they are - [Baidu banned from ILSVRC 2015](https://learnopencv.com/baidu-banned-from-ilsvrc-2015/) - Baidu's Deep Image team has been banned from ImageNet LSVRC 2015 for breaking the rules of the competition. A dark day for Deep Learning Research. - [Facial Landmark Detection](https://learnopencv.com/facial-landmark-detection/) - How to do track facial features in images and videos ? This post describes C++ / Python libraries and Web APIs for facial landmark detection. - [NVIDIA DIGITS 3 on EC2](https://learnopencv.com/nvidia-digits-3-on-ec2/) - Tutorial for installing NVIDIA DIGITS 3 (with Caffe & Torch support) on Amazon EC2. - [Speeding up Dlib's Facial Landmark Detector](https://learnopencv.com/speeding-up-dlib-facial-landmark-detector/) - In this tutorial we speed up Dlib's Facial Landmark Detector by 3x - [Image Recognition and Object Detection : Part 1](https://learnopencv.com/image-recognition-and-object-detection-part1/) - Image Recognition and Object Detection using traditional computer vision techniques like HOG and SVM. Deep Learning based methods to be covered in later posts. - [Deep Learning Book Gift](https://learnopencv.com/deep-learning-book-gift/) - It is almost the end of the year 2016 and this year I learned an important reason why the field of Artificial Intelligence is taking off. Yes, we now have access to huge amounts of data. Massive amounts of computational resources are at our fingertips, and AI algorithms are getting better every year. But, an - [Installing Deep Learning Frameworks on Ubuntu with CUDA support](https://learnopencv.com/installing-deep-learning-frameworks-on-ubuntu-with-cuda-support/) - Installing CUDA enabled Deep Learning frameworks - TernsorFlow, Pytorch, OpenCV on UBUNTU 16.04 with GTX 1080 Ti GPU - [Gaze Tracking](https://learnopencv.com/gaze-tracking/) - In this post, we provide an overview of gaze estimation and tracking algorithms and datasets. - [Install OpenCV 3 on Yosemite ( OSX 10.10.x )](https://learnopencv.com/install-opencv-3-on-yosemite-osx-10-10-x/) - A step by step tutorial for installing OpenCV 3 on Yosemite ( OSX 10.10.x ) with Python and CUDA support without messing up your OpenCV 2.4.x installation. - [Install OpenCV 3 on Yosemite ( OSX 10.10.x )](https://learnopencv.com/install-opencv-3-on-yosemite-osx-10-10-x/) - A step by step tutorial for installing OpenCV 3 on Yosemite ( OSX 10.10.x ) with Python and CUDA support without messing up your OpenCV 2.4.x installation. - [Deep Learning Example using NVIDIA DIGITS 3 on EC2](https://learnopencv.com/deep-learning-example-using-nvidia-digits-3-on-ec2/) - An Example of Deep Learning for image classification using NVIDIA DIGITS on Amazon EC2 - [Bias-Variance Tradeoff in Machine Learning](https://learnopencv.com/bias-variance-tradeoff-in-machine-learning/) - In this post, we explain the bias-variance tradeoff in machine learning and discuss ways to minimize errors. We also discuss the problem of model selection. - [Install OpenCV 3 on Windows](https://learnopencv.com/install-opencv3-on-windows/) - Step by step instruction for installing OpenCV 3 on Windows - [OpenCV Transparent API](https://learnopencv.com/opencv-transparent-api/) - How to use Transparent API ( T-API or TAPI ) in OpenCV 3 to significantly speed up existing code. TAPI uses OpenCL under the hood. - [Understanding AlexNet](https://learnopencv.com/understanding-alexnet/) - Understand the AlexNet architecture that won the ImageNet Visual Recognition Challenge in 2012 and started the Deep Learning revolution. - [Non-Photorealistic Rendering using OpenCV ( Python, C++ )](https://learnopencv.com/non-photorealistic-rendering-using-opencv-python-c/) - Explore Edge Preserving, Detail Enhance, Pencil Sketch, and Stylization filters in OpenCV with Python and C++ example code. - [Warp one triangle to another using OpenCV ( C++ / Python )](https://learnopencv.com/warp-one-triangle-to-another-using-opencv-c-python/) - This OpenCV (C++ / Python) tutorial explains how to warp a single triangle in an image to another triangle in a different image. - [High Dynamic Range (HDR) Imaging using OpenCV (C++/Python)](https://learnopencv.com/high-dynamic-range-hdr-imaging-using-opencv-cpp-python/) - Tutorial for creating High Dynamic Range (HDR) images and Tone mapping from multiple exposure images using OpenCV (C++ / Python). - [High Dynamic Range (HDR) Imaging using OpenCV (C++/Python)](https://learnopencv.com/high-dynamic-range-hdr-imaging-using-opencv-cpp-python/) - Tutorial for creating High Dynamic Range (HDR) images and Tone mapping from multiple exposure images using OpenCV (C++ / Python). - [Exposure Fusion using OpenCV (C++/Python)](https://learnopencv.com/exposure-fusion-using-opencv-cpp-python/) - Tutorial and code for Exposure Fusion using OpenCV (C++ / Python). Learn how to combine multiple exposure images into one optimally exposed image. - [Facemark : Facial Landmark Detection using OpenCV](https://learnopencv.com/facemark-facial-landmark-detection-using-opencv/) - Tutorial for OpenCV's Facemark API that implements three different algorithms for Facial Landmark Detection - FacemarkAAM, FacemarkKazemi and FacemarkLBF. Code is shared for real-time facial landmark detection - [How to convert your OpenCV C++ code into a Python module](https://learnopencv.com/how-to-convert-your-opencv-c-code-into-a-python-module/) - In this tutorial, we will learn how to compile your OpenCV C++ code into a Python module. We will share example code. - [Deep Learning based Character Classification using Synthetic Dataset](https://learnopencv.com/deep-learning-character-classification-using-synthetic-dataset/) - Character Classification using Synthetic Dataset. The dataset was generated using ImageMagick and A modified LeNet architecture was used for classification. - [Support Vector Machines (SVM)](https://learnopencv.com/support-vector-machines-svm/) - A math-free introduction to linear and non-linear Support Vector Machine (SVM). Learn about parameters C and Gamma, and Kernel Trick with Radial Basis Function. - [Heatmap for Logo Detection using OpenCV (Python)](https://learnopencv.com/heatmap-for-logo-detection-using-opencv-python/) - A tutorial for creating a heatmap to analyze the screen location of object annotations in video. We are sharing code in Python. - [Install OpenCV 4 on Ubuntu 16.04 (C++ and Python)](https://learnopencv.com/install-opencv-4-on-ubuntu-16-04/) - In this post, we will provide a bash script for installing OpenCV-4.0 (C++, Python 2.7 and Python 3.5) on Ubuntu 16.04. - [Install OpenCV from source on Windows – C++ / Python](https://learnopencv.com/install-opencv-4-on-windows/) - In this post, we will provide a batch script for installing OpenCV 4 (C++ and Python 3) on Windows. - [Universal Sentence Encoder](https://learnopencv.com/universal-sentence-encoder/) - In this blog post we will discuss about Sentence Encoding using Universal Sentence Encoder in Tensorflow Hub. We will also discuss an application of the same. - [Install OpenCV 3.4.4 on Raspberry Pi](https://learnopencv.com/install-opencv-3-4-4-on-raspberry-pi/) - In this post, we will provide a bash script for installing OpenCV 3.4.4 (C++, Python 2.7 and Python 3.5) on Raspbian Operating System on Raspberry Pi. - [Install OpenCV 4 on Red Hat (C++ and Python)](https://learnopencv.com/install-opencv-4-on-red-hat/) - In this post we will provide a bash script for installing OpenCV 4.0 on Red Hat Enterprise Linux 7 - [Install OpenCV 3.4.4 on CentOS 7 (C++ and Python)](https://learnopencv.com/install-opencv-3-4-4-on-centos-7/) - In this post we will provide a bash script for installing OpenCV 4.0 on CentOS 7 - [Using OpenVINO with OpenCV](https://learnopencv.com/using-openvino-with-opencv/) - Performance comparison of image classification, object detection and pose estimation tasks using OpenCV with OpenVINO and without OpenVINO. - [CNN Receptive Field Computation Using Backprop with TensorFlow](https://learnopencv.com/cnn-receptive-field-computation-using-backprop-with-tensorflow/) - Receptive Field helps us understand what a convolutional neural network "sees" in an image. We show the math and share Tensorflow/Keras code in this tutorial. - [CNN Receptive Field Computation Using Backprop](https://learnopencv.com/cnn-receptive-field-computation-using-backprop/) - How to understand which area on the input image is visible for the output pixel of the neural network. PyTorch code is shared. - [Multi-Label Image Classification with PyTorch: Image Tagging](https://learnopencv.com/multi-label-image-classification-with-pytorch-image-tagging/) - In the previous post, we learned how to apply a fixed number of tags to images. Let’s now switch to this broader task and see how we can tackle it. In many real-life tasks, there is a set of possible classes (also called tags) for data, and you would like to find some subset of - [Graph Convolutional Networks: Model Relations In Data](https://learnopencv.com/graph-convolutional-networks-model-relations-in-data/) - In an earlier post, we covered the problem of Multi Label Image Classification (MLIC) for Image Tagging. Recall that MLIC is an image classification task but unlike multi-class image classification or multi-output image classification, the number of labels an image can have isn't fixed. The differences are show in the table below. A classical approach - [Experiment Logging with TensorBoard and wandb](https://learnopencv.com/experiment-logging-with-tensorboard-and-wandb/) - When approaching a problem using Machine Learning or Deep Learning, researchers often face a necessity of model tuning because the chosen method usually depends on various hyperparameters and used data. The common way to tackle such problems is to start with implementing a baseline solution and measuring its quality. Then, the goal is to outperform - [Playing Chrome's T-Rex Game with Facial Gestures](https://learnopencv.com/playing-chromes-t-rex-game-with-facial-gestures/) - In this tutorial, you will learn to control Google's Chrome Dino game using your facial gestures by using OpenCV and Dlib. You will also learn to automate keyboard controls using python. - [PyTorch to CoreML model conversion](https://learnopencv.com/pytorch-to-coreml-model-conversion/) - Learn how to convert a PyTorch Model to ONNX and then to Apple CoreML format to be used on iOS devices. - [Creating a Virtual Pen And Eraser with OpenCV](https://learnopencv.com/creating-a-virtual-pen-and-eraser-with-opencv/) - In this post, you will learn how to create your own Virtual Pen & also a virtual eraser. This whole application will fundamentally be built on Contour Detection. - [How To Run Inference Using TensorRT C++ API](https://learnopencv.com/how-to-run-inference-using-tensorrt-c-api/) - Learn how to use the TensorRT C++ API to perform faster inference on your deep learning model - [Getting Started with OpenCV CUDA Module](https://learnopencv.com/getting-started-opencv-cuda-module/) - In this post, we will learn how to speed up OpenCV algorithms using CUDA on the example of Farneback Optical Flow - [Image Matting with state-of-the-art Method "F, B, Alpha Matting"](https://learnopencv.com/image-matting-with-state-of-the-art-method-f-b-alpha-matting/) - The foreground is the part of a view or picture, that is nearest to you when you look at it (Oxford dictionary). We, humans, are usually good at distinguishing foreground objects on images from the background. As computer vision algorithms became better and better at solving visual tasks it’s only natural we want to offload - [Tetris with OpenCV Python](https://learnopencv.com/tetris-with-opencv-python/) - In this post, we'll create the game of Tetris as shown in the video above. Tetris Most readers are probably familiar with Tetris - a popular and addictive video game created by Russian software engineer Alexey Pajitnov in 1984. Let's look at the parts of the game and the rules. Board The game consists of - [Image Classification with OpenCV Java](https://learnopencv.com/image-classification-with-opencv-java/) - Learn how to use the OpenCV Java API for Image Classification. Complete code is made available for a hands-on experience, study and practice. - [Hand Keypoint Detection using Deep Learning and OpenCV](https://learnopencv.com/hand-keypoint-detection-using-deep-learning-and-opencv/) - Learn Hand Keypoint Detection using OpenCV. We will briefly overview the network architecture discussed in paper. Code in C++ and Python is shared for practice. - [Gender and Age Classification using OpenCV Deep Learning ( C++/Python )](https://learnopencv.com/age-gender-classification-using-opencv-deep-learning-c-python/) - Would it be possible to determine age and gender using a single image? Yes. Follow this blog to learn Gender and Age Classification using OpenCV Deep Learning. - [Install OpenCV 4 on Raspberry Pi](https://learnopencv.com/install-opencv-4-on-raspberry-pi/) - Learn how-to install OpenCV 4 on Raspberry Pi. We've provided bash script for installing OpenCV (C++, Python 2.7 and Python 3.5) easily on your Raspberry Pi. - [Install OpenCV 3.4.4 on Ubuntu 18.04 (C++ and Python)](https://learnopencv.com/install-opencv-3-4-4-on-ubuntu-18-04/) - In this post we will provide a bash script for installing OpenCV 3.4.4 on Ubuntu 18.04 - [Install OpenCV 3.4.4 on Red Hat (C++ and Python)](https://learnopencv.com/install-opencv-3-4-4-on-red-hat/) - In this post we will provide a bash script for installing OpenCV 3.4.4 on Red Hat Enterprise Linux 7 - [Xeus-Cling: Run C++ code in Jupyter Notebook](https://learnopencv.com/xeus-cling-run-c-code-in-jupyter-notebook/) - In this post we discuss how to run C++ code in Jupyter Notebook using Xeus-Cling. - [Image Inpainting with OpenCV (C++/Python)](https://learnopencv.com/image-inpainting-with-opencv-c-python/) - In this post, we explain a method for image restoration called image inpainting. We are sharing OpenCV code in C++ and Python. - [Funny Mirrors Using OpenCV](https://learnopencv.com/funny-mirrors-using-opencv/) - We all remember those awesome childhood days when we use to go to amusement parks or county fairs. One of my favorite elements of these amusement parks was the fun-house mirror room. Funny mirrors are not plane mirrors but a combination of convex/concave reflective surfaces that produce distortion effects that look funny as we move - [Getting Started with PyTorch Lightning](https://learnopencv.com/getting-started-with-pytorch-lightning/) - Throughout this blog, we will learn how can Lightning be used along with PyTorch to make development easy and reproducible. - [Install OpenCV 3 on MacOS](https://learnopencv.com/install-opencv3-on-macos/) - Step by step instructions for installing OpenCV 3 (C++ and Python) on MacOS and OSX. - [Install Dlib on Ubuntu](https://learnopencv.com/install-dlib-on-ubuntu/) - Step by step instructions on how to install Dlib on Ubuntu (C++ and Python). We will also show how to compile example code. - [Number of Parameters and Tensor Sizes in a Convolutional Neural Network (CNN)](https://learnopencv.com/number-of-parameters-and-tensor-sizes-in-convolutional-neural-network/) - How to calculate the sizes of tensors (images) and the number of parameters in a layer in a Convolutional Neural Network (CNN). We share formulas with AlexNet as an example. - [Embedded Vision Summit 2015](https://learnopencv.com/embedded-vision-summit-2015/) - Embedded Vision Summit 2015 is a top Computer Vision industry conference. Speakers include Dr. Gary Bradski ( OpenCV) and Dr. Ren Wu ( Baidu ). - [How to find OpenCV version in Python and C++ ?](https://learnopencv.com/how-to-find-opencv-version-python-cpp/) - Easy ways to detect OpenCV version in Python and C++. Example code provided. - [Approximate Focal Length for Webcams and Cell Phone Cameras](https://learnopencv.com/approximate-focal-length-for-webcams-and-cell-phone-cameras/) - This tutorial explains a way to find a crude approximation to the focal length of a webcam or cell phone camera. - [Training a better Haar and LBP cascade based Eye Detector using OpenCV](https://learnopencv.com/training-better-haar-lbp-cascade-eye-detector-opencv/) - In this tutorial, we show how we trained Haar and LBP cascade based eye detectors that out-perform OpenCV default eye detectors. - [Install Dlib on MacOS](https://learnopencv.com/install-dlib-on-macos/) - Step by step instructions for installing Dlib (C++ / Python) on MacOS and OSX. - [Install OpenCV3 on Ubuntu](https://learnopencv.com/install-opencv3-on-ubuntu/) - In this post, we will provide step by step instructions for installing OpenCV 3 (C++ and Python) on Ubuntu. - [Install Dlib on Windows](https://learnopencv.com/install-dlib-on-windows/) - Step by step instructions on how to install Dlib (C++ / Python) on Windows. - [Install OpenCV 3 and Dlib on Windows ( Python only )](https://learnopencv.com/install-opencv-3-and-dlib-on-windows-python-only/) - In this tutorial, we discuss the simple steps to install OpenCV on Windows for Python users. - [Ensuring Training Reproducibility in PyTorch](https://learnopencv.com/ensuring-training-reproducibility-in-pytorch/) - This blog post shows how to do reproducible training of deep learning models in PyTorch. - [Face Swap using OpenCV ( C++ / Python )](https://learnopencv.com/face-swap-using-opencv-c-python/) - In this tutorial we will learn how to swap out a face in one image with a completely different face using OpenCV and DLib in C++ and Python. Ladies and gentlemen, let me present Ted Trump, Donald Clinton and Hillary Cruz. Do you like any of them ? Me neither! I know, I know, I know, the above - [Parallel Pixel Access in OpenCV using forEach](https://learnopencv.com/parallel-pixel-access-in-opencv-using-foreach/) - Comparing the performance of the forEach method of the Mat class to other ways of accessing and transforming pixel values in OpenCV. - [Selective Search for Object Detection (C++ / Python)](https://learnopencv.com/selective-search-for-object-detection-cpp-python/) - This tutorial explains selective search for object detection with OpenCV C++ and Python code. - [OpenCV Installation on Ubuntu, macOS, Windows and Raspberry Pi](https://learnopencv.com/opencv-installation-on-ubuntu-macos-windows-and-raspberry-pi/) - In this short post we will summarise OpenCV Installation on different Operating Systems. - [How to train a Deep Learning based Image Classifier in MacOS](https://learnopencv.com/how-to-train-a-deep-learning-based-image-classifier-in-macos/) - In this tutorial, we discuss how to use Apple's Deep Learning Tool called CreateML to train deep learning based image classifier. - [PyTorch C++ Front-end: Tensors](https://learnopencv.com/pytorch-c-front-end-tensors/) - In this blog we will discuss how libtorch can be setup. We will also focus on creating and reshaping tensors using the PyTorch C++ front-end. - [Install OpenCV on Android  : Tiny and Optimized](https://learnopencv.com/install-opencv-on-android-tiny-and-optimized/) - Step by step instructions for Installing optimized and tiny OpenCV library on Android. - [CPU Performance Comparison of OpenCV and other Deep Learning frameworks](https://learnopencv.com/cpu-performance-comparison-of-opencv-and-other-deep-learning-frameworks/) - Performance comparison ( Image Classification, Object Detection, Tracking, and Pose Estimation ) of OpenCV with DL frameworks for inference on a CPU. - [Cropping an Image using OpenCV](https://learnopencv.com/cropping-an-image-using-opencv/) - Learn how cropping an image using OpenCV works. Also, learn how you can divide an image into smaller patches using cropping. - [NVIDIA GTC 2022 Day 1 Highlights: Brilliant Start](https://learnopencv.com/gtc-day-1-highlights/) - This post brings you NVIDIA GTC Day 1 Highlights First day had sessions on topics from physics simulation to anomaly detection cybersecurity & 3D deep learning - [NVIDIA GTC 2022 Day 2 Highlights: Jensen's Keynote](https://learnopencv.com/nvidia-gtc-2022-day-2-highlights/) - Day 2 coverage of the NVIDIA GTC conference includes topics like Jensen’s keynote, Hopper H100 GPU, Building a career in AI, and more. - [Top 10 Sources to Find Computer Vision and AI Models](https://learnopencv.com/top-10-sources-to-find-computer-vision-and-ai-models/) - In this post, we will look at the list of popular sources where you can find different Deep Learning Models to jump-start your Machine Learning application. - [Top 10 Sources to Find Computer Vision and AI Models](https://learnopencv.com/top-10-sources-to-find-computer-vision-and-ai-models/) - In this post, we will look at the list of popular sources where you can find different Deep Learning Models to jump-start your Machine Learning application. - [Variational Autoencoder in TensorFlow](https://learnopencv.com/variational-autoencoder-in-tensorflow/) - Learn about Variational Autoencoder in TensorFlow. Implement VAE in TensorFlow on Fashion-MNIST and Cartoon Dataset. Compare latent space of VAE and AE. - [Variational Autoencoder in TensorFlow](https://learnopencv.com/variational-autoencoder-in-tensorflow/) - Learn about Variational Autoencoder in TensorFlow. Implement VAE in TensorFlow on Fashion-MNIST and Cartoon Dataset. Compare latent space of VAE and AE. - [Playing Chrome's T-Rex Game with Facial Gestures](https://learnopencv.com/playing-chromes-t-rex-game-with-facial-gestures/) - In this tutorial, you will learn to control Google's Chrome Dino game using your facial gestures by using OpenCV and Dlib. You will also learn to automate keyboard controls using python. - [Funny Mirrors Using OpenCV](https://learnopencv.com/funny-mirrors-using-opencv/) - We all remember those awesome childhood days when we use to go to amusement parks or county fairs. One of my favorite elements of these amusement parks was the fun-house mirror room. Funny mirrors are not plane mirrors but a combination of convex/concave reflective surfaces that produce distortion effects that look funny as we move ## Pages - [Home](https://learnopencv.com/) - Master Computer Vision, Deep Learning, and AI with expert tutorials, code examples, and guides. Learn OpenCV in Python & C++ — from beginner to advanced. - [Pause Marketing](https://learnopencv.com/pause-marketing/) - You have been unsubscribed from Independence Day 2026 Sale emails. - [Getting Started with OpenCV](https://learnopencv.com/getting-started-with-opencv/) - A series of tutorial for getting started in OpenCV - the biggest computer vision library in the world. Learn to build real world application in just a few hours! - [Getting Started with OpenCV](https://learnopencv.com/getting-started-with-opencv/) - A series of tutorial for getting started in OpenCV - the biggest computer vision library in the world. Learn to build real world application in just a few hours! - [Getting Started with OpenCV](https://learnopencv.com/getting-started-with-opencv/) - A series of tutorial for getting started in OpenCV - the biggest computer vision library in the world. Learn to build real world application in just a few hours! - [Getting Started with OpenCV](https://learnopencv.com/getting-started-with-opencv/) - A series of tutorial for getting started in OpenCV - the biggest computer vision library in the world. Learn to build real world application in just a few hours! - [Computer Vision and Machine Learning (Artificial Intelligence) Consulting](https://learnopencv.com/computer-vision-machine-learning-artificial-intelligence-consulting/) - Dr. Satya Mallick is an expert in Computer Vision and Machine Learning. In Feb. 2017, IBM's AI blog named him among the top 30 most influential AI experts to follow on Twitter. He has also featured in numerous online articles and blogs including the Huffington Post, TechCrunch and the Register to name a few. In - [About](https://learnopencv.com/about/) - I am Satya Mallick. I blog about Computer Vision and Machine Learning, and publish code and tutorials in OpenCV ( C++ & Python ). - [WIN A FREE NVIDIA RTX 4080 GPU](https://learnopencv.com/win-a-free-nvidia-4080-gpu/) - WIN A FREE NVIDIA RTX 4080 GPU They say you cannot build a Deep Learning workstation these days because GPUs are in such short supply. While that may be true, I have a direct connection with the GPU Gods at NVIDIA who have very kindly sponsored the following giveaways for our newsletter subscribers. NVIDIA 4080 - [Getting Started with Keras & Tensorflow](https://learnopencv.com/getting-started-with-tensorflow-keras/) - At Learnopencv.com, we have adopted a mission of spreading awareness and educating a global workforce in Artificial Intelligence. Taking a step further in that direction, we have started creating tutorials for getting started in Deep Learning with Keras. We hope that this will be helpful for people who want to get started in Deep Learning - [Getting Started with PyTorch](https://learnopencv.com/getting-started-with-pytorch/) - At Learnopencv.com, we have adopted a mission of spreading awareness and educate a global workforce on Artificial Intelligence. Taking a step further in that direction, we have started creating tutorials for getting started in Deep Learning with PyTorch. We hope that this will be helpful for people who want to get started in Deep Learning - [Learn Keras and Tensorflow](https://learnopencv.com/learn-keras-and-tensorflow/) - At LearnOpenCV.com, we have adopted a mission of helping people take their first steps in the fields of Machine Learning, Computer Vision, Deep Learning, and AI. We have created a series of tutorials for absolute beginners to get started with Deep Learning using Keras and TensorFlow. Although you can find a lot of tutorials on - [Official OpenCV Courses](https://learnopencv.com/official-opencv-courses/) - A few years ago I started getting a lot of email from subscribers asking for detailed, step-by-step coverage of key Computer Vision and OpenCV topics. When I asked if there any interest in a comprehensive course, the response was an overwhelming “YES”! From there I created an initial course called CV4Faces that my subscribers loved. - [Deep Learning and Computer Vision Demos](https://learnopencv.com/deep-learning-and-computer-vision-demos/) - Explore the demos of the various Computer Vision and Deep Learning applications developed at LearnOpenCV Document Scanner Application using OpenCV Check out the demo of our Automatic Document Scanner built using OpenCV Try it Out Deep Learning based Document Scanner We train a DeepLabv3 Semantic Segmentation model of document Scanning. Read More Image Annotation Tool - [WIN A FREE NVIDIA 3080 Ti GPU](https://learnopencv.com/win-a-free-nvidia-3080-ti-gpu-2022/) - They say you cannot build a Deep Learning workstation these days because GPUs are in such short supply. - [The Complete Guide to Object Tracking - OpenCV, DeepSort, FairMOT](https://learnopencv.com/the-complete-guide-to-object-tracking-in-computer-vision/) - Object Tracking is the process of finding objects and keeping track of their trajectories in a video sequence. We provide a complete guide for Object Tracking in this article. - [LearnOpenCV](https://learnopencv.com/home-b/) - Learn Computer Vision, Deep Learning, and Artificial Intelligence concepts, and tutorials, and get career advice. Subscribe for FREE! - [WIN A FREE NVIDIA 3080 Ti GPU](https://learnopencv.com/win-a-free-nvidia-3080-ti-gpu/) - Thanks for your interest in NVIDIA GTC 2022. Registration through LearnOpenCV is now CLOSED after the successful completion of the GTC 2022 conference on 24th March 2022. - [Blog Olympics](https://learnopencv.com/blog-olympics/) - 26th Oct - 6th Dec LearnOpenCV Blog Olympics No, it’s not in Tokyo. But online. Grand Prize Winners #2 Floris Alexandrou Fighting Climate Change UsingComputer Vision #1 Anton Moscowsky Multiattribute and Graph-based Object Detection #3 Enrique Dehaerne Ensemble Deep Learning-based Defect Classification and Detection in SEM Images Other Finalists Name Blogpost Title Nguyen Viet Anh - [Blog Olympics Submission](https://learnopencv.com/blog-olympics-submission/) - 26th Oct - 6th Dec LearnOpenCV Blog Olympics No, it’s not in Tokyo. But online. You should submit the write-up along with the code and a Demo video of running the code and showing the output. You can submit them by uploading them to a Google Drive / Dropbox and providing the link in the - [Learn PyTorch](https://learnopencv.com/learn-pytorch/) - At Learnopencv.com, we have adopted a mission of spreading awareness and educate a global workforce on Artificial Intelligence. Taking a step further in that direction, we have started creating tutorials for getting started in Deep Learning with PyTorch. We hope that this will be helpful for people who want to get started in Deep Learning - [Data Annotation Services](https://learnopencv.com/data-annotation-services/) - We do in house annotations for many of our projects, as well as use third party services, in case of larger projects. One of our main collaborators in for annotations is rProcess. rProcess is a team based in India. They offer many data annotation capabilities, including semantic segmentation, image segmentation, data labelling, named entity recognition - [CV4Faces](https://learnopencv.com/cv4faces/) - [Blog Olympics](https://learnopencv.com/blog-olympics/) - 26th Oct - 6th Dec LearnOpenCV Blog Olympics No, it’s not in Tokyo. But online. Grand Prize Winners #2 Floris Alexandrou Fighting Climate Change UsingComputer Vision #1 Anton Moscowsky Multiattribute and Graph-based Object Detection #3 Enrique Dehaerne Ensemble Deep Learning-based Defect Classification and Detection in SEM Images Other Finalists Name Blogpost Title Nguyen Viet Anh - [Blog Olympics](https://learnopencv.com/blog-olympics/) - 26th Oct - 6th Dec LearnOpenCV Blog Olympics No, it’s not in Tokyo. But online. Grand Prize Winners #2 Floris Alexandrou Fighting Climate Change UsingComputer Vision #1 Anton Moscowsky Multiattribute and Graph-based Object Detection #3 Enrique Dehaerne Ensemble Deep Learning-based Defect Classification and Detection in SEM Images Other Finalists Name Blogpost Title Nguyen Viet Anh ## Categories - [Uncategorized](https://learnopencv.com/category/uncategorized/) - [Install OpenCV](https://learnopencv.com/category/install/) - [Object Detection](https://learnopencv.com/category/object-detection/) - [OpenCV 3](https://learnopencv.com/category/opencv-3/) - [Non-Photorealistic Rendering](https://learnopencv.com/category/non-photorealistic-rendering/) - [Conferences](https://learnopencv.com/category/conferences/) - [Machine Learning](https://learnopencv.com/category/machine-learning/) - [Deep Learning](https://learnopencv.com/category/deep-learning/) - [Image Alignment](https://learnopencv.com/category/image-alignment/) - [Tutorial](https://learnopencv.com/category/tutorial/) - [Image Classification](https://learnopencv.com/category/image-classification/) - [Image Recognition](https://learnopencv.com/category/image-recognition/) - [Tracking](https://learnopencv.com/category/tracking/) - [Segmentation](https://learnopencv.com/category/segmentation/) - [UI](https://learnopencv.com/category/ui/) - [GUI](https://learnopencv.com/category/gui/) - [Courses](https://learnopencv.com/category/courses/) - [Awards](https://learnopencv.com/category/awards/) - [Text Recognition](https://learnopencv.com/category/text-recognition/) - [OCR](https://learnopencv.com/category/ocr/) - [OpenCV 4](https://learnopencv.com/category/opencv-4/) - [Testimonials](https://learnopencv.com/category/testimonials/) - [Shape Analysis](https://learnopencv.com/category/shape-analysis/) - [Android](https://learnopencv.com/category/android/) - [Feature Detection](https://learnopencv.com/category/feature-detection/) - [Image Processing](https://learnopencv.com/category/image-processing/) - [PyTorch](https://learnopencv.com/category/pytorch/) - [Keras](https://learnopencv.com/category/keras/) - [Tensorflow](https://learnopencv.com/category/tensorflow/) - [Video Analysis](https://learnopencv.com/category/video-analysis/) - [Camera Calibration](https://learnopencv.com/category/camera-calibration/) - [Structure From Motion](https://learnopencv.com/category/structure-from-motion/) - [Edge Devices](https://learnopencv.com/category/edge-devices/) - [Java](https://learnopencv.com/category/java/) - [Classical Computer Vision](https://learnopencv.com/category/classical-computer-vision/) - Dive into Classical Computer Vision to master foundational techniques and algorithms that enable computers to interpret and understand visual data. - [Paper Overview](https://learnopencv.com/category/paper-overview/) - [PyTorch-Lightning](https://learnopencv.com/category/pytorch-lightning/) - [Competitions](https://learnopencv.com/category/competitions/) - [Medical Imaging](https://learnopencv.com/category/medical-imaging/) - [3D Computer Vision](https://learnopencv.com/category/3d-computer-vision/) - [OAK](https://learnopencv.com/category/oak/) - [OpenCV](https://learnopencv.com/category/opencv/) - [Beginners](https://learnopencv.com/category/beginners/) - [Face Recognition](https://learnopencv.com/category/face-recognition/) - [Generative Adversarial Networks](https://learnopencv.com/category/generative-adversarial-networks/) - Discover Generative Adversarial Networks (GANs): Explore the architecture, applications, and innovations in AI that are revolutionizing content generation - [Computer Vision](https://learnopencv.com/category/computer-vision/) - [Windows](https://learnopencv.com/category/windows/) - [OpenCV DNN](https://learnopencv.com/category/opencv-dnn/) - [OpenCV Beginners](https://learnopencv.com/category/opencv-beginners/) - [OpenCV Tutorials](https://learnopencv.com/category/opencv-tutorials/) - [Homography](https://learnopencv.com/category/homography/) - [Object Tracking](https://learnopencv.com/category/object-tracking/) - [Raspberry Pi](https://learnopencv.com/category/raspberry-pi/) - [Image Segmentation](https://learnopencv.com/category/image-segmentation/) - [Tensorflow Tutorials](https://learnopencv.com/category/tensorflow-tutorials/) - [Face Detection](https://learnopencv.com/category/face-detection/) - [DLIB](https://learnopencv.com/category/dlib/) - [Face Application](https://learnopencv.com/category/face-application/) - [Text Detection](https://learnopencv.com/category/text-detection/) - [Getting Started with OpenCV](https://learnopencv.com/category/getting-start-with-opencv/) - Begin your journey in computer vision with 'Getting Started with OpenCV': Learn the basics of image processing and real-time video manipulation. - [Intel OpenVINO Toolkit](https://learnopencv.com/category/intel-openvino-toolkit/) - [Post Training Quantization](https://learnopencv.com/category/post-training-quantization/) - [Model Optimization](https://learnopencv.com/category/model-optimization/) - [CNN](https://learnopencv.com/category/cnn/) - Discover Convolutional Neural Networks: essential deep learning technology for image recognition and analysis, driving advancements in AI and computer vision - [MediaPipe](https://learnopencv.com/category/mediapipe/) - [Pose Estimation](https://learnopencv.com/category/pose-estimation/) - [GTC](https://learnopencv.com/category/gtc/) - [NVIDIA](https://learnopencv.com/category/nvidia/) - [YOLO](https://learnopencv.com/category/yolo/) - Uncover YOLO (You Only Look Once): A game-changing object detection algorithm series known for its speed and accuracy in real-time applications. - [Face Authentication](https://learnopencv.com/category/face-authentication/) - [DeepSORT](https://learnopencv.com/category/deepsort/) - [GPUs](https://learnopencv.com/category/gpus/) - [CUDA](https://learnopencv.com/category/cuda/) - [Image Registration](https://learnopencv.com/category/image-registration/) - [Streamlit](https://learnopencv.com/category/streamlit/) - [CenterNet](https://learnopencv.com/category/object-detection/centernet/) - [Anchor-free](https://learnopencv.com/category/object-detection/anchor-free-object-detection-2/) - [FCOS](https://learnopencv.com/category/object-detection/anchor-free-object-detection-2/fcos/) - [Training Neural Networks](https://learnopencv.com/category/training-neural-networks/) - [Gradient Descent](https://learnopencv.com/category/gradient-descent/) - [Linear Regrerssion](https://learnopencv.com/category/linear-regrerssion/) - [Neural Network](https://learnopencv.com/category/neural-network/) - [Getting started with Tensorflow & Keras](https://learnopencv.com/category/getting-start-with-keras-tensorflow/) - Start your deep learning journey with TensorFlow & Keras: Build, train, and deploy models efficiently with our step-by-step guides - [Annotation Tool](https://learnopencv.com/category/annotation-tool/) - [Pooling Layers](https://learnopencv.com/category/pooling-layers/) - [Convolution](https://learnopencv.com/category/convolution/) - [Getting Started with PyTorch](https://learnopencv.com/category/getting-started-with-pytorch/) - Kickstart your deep learning with 'Getting Started with PyTorch': Learn to build neural networks and harness GPU power for AI projects - [Diffusion Models](https://learnopencv.com/category/diffusion-models/) - [Generative Models](https://learnopencv.com/category/generative-models/) - [Deployment](https://learnopencv.com/category/deployment/) - [Neural Attention](https://learnopencv.com/category/neural-attention/) - [Transformer Neural Networks](https://learnopencv.com/category/transformer-neural-networks/) - [AI Art Generation](https://learnopencv.com/category/ai-art-generation/) - [Vision Transformer](https://learnopencv.com/category/vision-transformer/) - [PyPi Packaging](https://learnopencv.com/category/pypi-packaging/) - [Background Estimation](https://learnopencv.com/category/background-estimation/) - [Loss Function](https://learnopencv.com/category/loss-function/) - [Drone Programming](https://learnopencv.com/category/drone-programming/) - [Artificial Intelligence](https://learnopencv.com/category/artificial-intelligence/) - [Keypoint Estimation](https://learnopencv.com/category/keypoint-estimation/) - [keypoint detection](https://learnopencv.com/category/keypoint-detection/) - [Similarity Measure](https://learnopencv.com/category/similarity-measure/) - [Facial Expression Recognition](https://learnopencv.com/category/facial-expression-recognition/) - [Hugging Face Transformers](https://learnopencv.com/category/hugging-face-transformers/) - [AI Research Papers](https://learnopencv.com/category/ai-research-papers/) - [Advanced Driver Assistance Systems](https://learnopencv.com/category/advanced-driver-assistance-systems/) - Explore 'Advanced Driver Assistance Systems' to understand how ADAS improves safety and comfort with cutting-edge driving technology solutions. - [NLP](https://learnopencv.com/category/nlp/) - [Language Models](https://learnopencv.com/category/language-models/) - [SIoU Loss Functions](https://learnopencv.com/category/yolo/siou-loss-functions/) - [Focal Loss](https://learnopencv.com/category/yolo/focal-loss/) - [GFL](https://learnopencv.com/category/yolo/gfl/) - [VFL](https://learnopencv.com/category/yolo/vfl/) - [LLMs](https://learnopencv.com/category/llms/) - Explore Large Language Models (LLMs) in our dedicated category, covering their breakthroughs in understanding and generating human language with AI - [Generative AI](https://learnopencv.com/category/generative-ai/) - Generative AI: the cutting-edge tech reshaping creativity and problem-solving in AI through innovative data generation, including images, texts, & designs - [Robotics](https://learnopencv.com/category/robotics/) - [ROS](https://learnopencv.com/category/robotics/ros/) - [SLAM](https://learnopencv.com/category/computer-vision/slam/) - [Speech Recognition](https://learnopencv.com/category/speech-recognition/) - [Autonomous Vehicle](https://learnopencv.com/category/robotics/autonomous-vehicle/) - [Speech AI](https://learnopencv.com/category/speech-ai/) - [Voice AI](https://learnopencv.com/category/voice-ai/) - [Self-Supervised Learning](https://learnopencv.com/category/self-supervised-learning/) - [Contrastive Learning](https://learnopencv.com/category/contrastive-learning/) - [SpatialAI-Depth](https://learnopencv.com/category/3d-computer-vision/spatialai-depth/) - [3D Computer Graphics](https://learnopencv.com/category/3d-computer-vision/3d-computer-graphics/) - [Vision Language Models](https://learnopencv.com/category/generative-ai/vision-language-models/) - [Agentic AI](https://learnopencv.com/category/agentic-ai/) - [3D Reconstruction](https://learnopencv.com/category/3d-computer-vision/3d-reconstruction/) - [RAGs](https://learnopencv.com/category/llms/rags/) - [Video Matting](https://learnopencv.com/category/video-matting/) - [Feature Matching](https://learnopencv.com/category/structure-from-motion/feature-matching/) - [Multimodal Models](https://learnopencv.com/category/generative-models/multimodal-models/) - [video diffusion](https://learnopencv.com/category/diffusion-models/video-diffusion/) - [video classification](https://learnopencv.com/category/generative-ai/vision-language-models/video-classification/) - [VLMs](https://learnopencv.com/category/vlms/) - [Anomaly Detection](https://learnopencv.com/category/anomaly-detection/) - [Jetson Nano](https://learnopencv.com/category/edge-devices/jetson-nano/) - [VLM on Jetson Nano](https://learnopencv.com/category/edge-devices/jetson-nano/vlm-on-jetson-nano/) - [2D Reconstruction](https://learnopencv.com/category/2d-reconstruction/) - [OpenCV 5](https://learnopencv.com/category/opencv/opencv-5/) ## Tags - [Yosemite](https://learnopencv.com/tag/yosemite/) - [OSX 10.10.x](https://learnopencv.com/tag/osx-10-10-x/) - [Build from source](https://learnopencv.com/tag/build-from-source/) - [OpenCV](https://learnopencv.com/tag/opencv/) - [pkg-config](https://learnopencv.com/tag/pkg-config/) - [how to](https://learnopencv.com/tag/how-to/) - [compile](https://learnopencv.com/tag/compile/) - [sample](https://learnopencv.com/tag/sample/) - [PythonAnywhere.com](https://learnopencv.com/tag/pythonanywhere-com/) - [Web2PY](https://learnopencv.com/tag/web2py/) - [Web API](https://learnopencv.com/tag/web-api/) - [Web Service](https://learnopencv.com/tag/web-service/) - [Blob Detector](https://learnopencv.com/tag/blob-detector/) - [C++](https://learnopencv.com/tag/c/) - [Python](https://learnopencv.com/tag/python/) - [threshold](https://learnopencv.com/tag/threshold/) - [Seamless Cloning](https://learnopencv.com/tag/seamless-cloning/) - [Poisson Image Editing](https://learnopencv.com/tag/poisson-image-editing/) - [edgePreservingFilter](https://learnopencv.com/tag/edgepreservingfilter/) - [detailEnhance](https://learnopencv.com/tag/detailenhance/) - [pencilSketch](https://learnopencv.com/tag/pencilsketch/) - [stylization](https://learnopencv.com/tag/stylization/) - [OpenCV 3](https://learnopencv.com/tag/opencv-3/) - [npr](https://learnopencv.com/tag/npr/) - [imread](https://learnopencv.com/tag/imread/) - [IMREAD_UNCHANGED](https://learnopencv.com/tag/imread_unchanged/) - [IMREAD_ANYDEPTH](https://learnopencv.com/tag/imread_anydepth/) - [IMREAD_ANYCOLOR](https://learnopencv.com/tag/imread_anycolor/) - [IMREAD_GRAYSCALE](https://learnopencv.com/tag/imread_grayscale/) - [IMREAD_COLOR](https://learnopencv.com/tag/imread_color/) - [Read Image](https://learnopencv.com/tag/read-image/) - [Embedded Vision Summit](https://learnopencv.com/tag/embedded-vision-summit/) - [World Cup Soccer 1966](https://learnopencv.com/tag/world-cup-soccer-1966/) - [Andrew Zisserman](https://learnopencv.com/tag/andrew-zisserman/) - [Wembley Goal](https://learnopencv.com/tag/wembley-goal/) - [Goal Line Technology](https://learnopencv.com/tag/goal-line-technology/) - [tapi](https://learnopencv.com/tag/tapi/) - [t-api](https://learnopencv.com/tag/t-api/) - [hardware acceleration](https://learnopencv.com/tag/hardware-acceleration/) - [transparent API](https://learnopencv.com/tag/transparent-api/) - [opencl](https://learnopencv.com/tag/opencl/) - [baidu](https://learnopencv.com/tag/baidu/) - [ILSVRC 2015](https://learnopencv.com/tag/ilsvrc-2015/) - [version](https://learnopencv.com/tag/version/) - [image alignment](https://learnopencv.com/tag/image-alignment/) - [homography](https://learnopencv.com/tag/homography/) - [affine](https://learnopencv.com/tag/affine/) - [warpAffine](https://learnopencv.com/tag/warpaffine/) - [warpPerspective](https://learnopencv.com/tag/warpperspective/) - [findTransformECC](https://learnopencv.com/tag/findtransformecc/) - [Prokudin-Gorskii](https://learnopencv.com/tag/prokudin-gorskii/) - [image registration](https://learnopencv.com/tag/image-registration/) - [applyColorMap](https://learnopencv.com/tag/applycolormap/) - [colormap](https://learnopencv.com/tag/colormap/) - [custom colormap](https://learnopencv.com/tag/custom-colormap/) - [LUT](https://learnopencv.com/tag/lut/) - [numpy](https://learnopencv.com/tag/numpy/) - [facial attrativeness](https://learnopencv.com/tag/facial-attrativeness/) - [scikit-learn](https://learnopencv.com/tag/scikit-learn/) - [regression](https://learnopencv.com/tag/regression/) - [linear regression](https://learnopencv.com/tag/linear-regression/) - [CLM-framework](https://learnopencv.com/tag/clm-framework/) - [BGR](https://learnopencv.com/tag/bgr/) - [dlib](https://learnopencv.com/tag/dlib/) - [facial feature detection](https://learnopencv.com/tag/facial-feature-detection/) - [keypoint detection](https://learnopencv.com/tag/keypoint-detection/) - [matlab](https://learnopencv.com/tag/matlab/) - [delaunay](https://learnopencv.com/tag/delaunay/) - [triangulation](https://learnopencv.com/tag/triangulation/) - [voronoi](https://learnopencv.com/tag/voronoi/) - [tesselation](https://learnopencv.com/tag/tesselation/) - [fps](https://learnopencv.com/tag/fps/) - [frame rate](https://learnopencv.com/tag/frame-rate/) - [frames per second](https://learnopencv.com/tag/frames-per-second/) - [imfill](https://learnopencv.com/tag/imfill/) - [holes](https://learnopencv.com/tag/holes/) - [panorama](https://learnopencv.com/tag/panorama/) - [perspective correction](https://learnopencv.com/tag/perspective-correction/) - [nvidia](https://learnopencv.com/tag/nvidia/) - [digits](https://learnopencv.com/tag/digits/) - [convolutional neural network](https://learnopencv.com/tag/convolutional-neural-network/) - [cnn](https://learnopencv.com/tag/cnn/) - [DNN](https://learnopencv.com/tag/dnn/) - [NVIDIA DIGITS 3](https://learnopencv.com/tag/nvidia-digits-3/) - [Amazon EC2](https://learnopencv.com/tag/amazon-ec2/) - [Image Classification](https://learnopencv.com/tag/image-classification/) - [Face Morphing](https://learnopencv.com/tag/face-morphing/) - [convex hull](https://learnopencv.com/tag/convex-hull/) - [face swap](https://learnopencv.com/tag/face-swap/) - [face replace](https://learnopencv.com/tag/face-replace/) - [face averaging](https://learnopencv.com/tag/face-averaging/) - [face alignment](https://learnopencv.com/tag/face-alignment/) - [average face](https://learnopencv.com/tag/average-face/) - [affine transform](https://learnopencv.com/tag/affine-transform/) - [triangle warping](https://learnopencv.com/tag/triangle-warping/) - [fillConvexPoly](https://learnopencv.com/tag/fillconvexpoly/) - [geometry](https://learnopencv.com/tag/geometry/) - [euler](https://learnopencv.com/tag/euler/) - [rotation](https://learnopencv.com/tag/rotation/) - [Tait–Bryan](https://learnopencv.com/tag/tait-bryan/) - [qt](https://learnopencv.com/tag/qt/) - [focal length](https://learnopencv.com/tag/focal-length/) - [field of view](https://learnopencv.com/tag/field-of-view/) - [sensor size](https://learnopencv.com/tag/sensor-size/) - [live cv](https://learnopencv.com/tag/live-cv/) - [coding](https://learnopencv.com/tag/coding/) - [application](https://learnopencv.com/tag/application/) - [qml](https://learnopencv.com/tag/qml/) - [Head Pose](https://learnopencv.com/tag/head-pose/) - [Pose](https://learnopencv.com/tag/pose/) - [solvepnp](https://learnopencv.com/tag/solvepnp/) - [solvepnpransac](https://learnopencv.com/tag/solvepnpransac/) - [Image Recognition](https://learnopencv.com/tag/image-recognition/) - [Object Detection](https://learnopencv.com/tag/object-detection/) - [Histogram of Oriented Gradients](https://learnopencv.com/tag/histogram-of-oriented-gradients/) - [Support Vector Machine](https://learnopencv.com/tag/support-vector-machine/) - [HOG](https://learnopencv.com/tag/hog/) - [SVM](https://learnopencv.com/tag/svm/) - [feature descriptor](https://learnopencv.com/tag/feature-descriptor/) - [book](https://learnopencv.com/tag/book/) - [haar](https://learnopencv.com/tag/haar/) - [cascades](https://learnopencv.com/tag/cascades/) - [lbp](https://learnopencv.com/tag/lbp/) - [Eye Detector](https://learnopencv.com/tag/eye-detector/) - [BOOSTING](https://learnopencv.com/tag/boosting/) - [TLD](https://learnopencv.com/tag/tld/) - [MIL](https://learnopencv.com/tag/mil/) - [KCL](https://learnopencv.com/tag/kcl/) - [GOTURN](https://learnopencv.com/tag/goturn/) - [MEDIANFLOW](https://learnopencv.com/tag/medianflow/) - [object tracking](https://learnopencv.com/tag/object-tracking/) - [Embedded Vision](https://learnopencv.com/tag/embedded-vision/) - [Raspberry Pi](https://learnopencv.com/tag/raspberry-pi/) - [Jetson](https://learnopencv.com/tag/jetson/) - [bias](https://learnopencv.com/tag/bias/) - [variance](https://learnopencv.com/tag/variance/) - [model selection](https://learnopencv.com/tag/model-selection/) - [red-eye](https://learnopencv.com/tag/red-eye/) - [eyes](https://learnopencv.com/tag/eyes/) - [bounding box](https://learnopencv.com/tag/bounding-box/) - [roi](https://learnopencv.com/tag/roi/) - [ios](https://learnopencv.com/tag/ios/) - [facial landmark detection](https://learnopencv.com/tag/facial-landmark-detection/) - [alpha blending](https://learnopencv.com/tag/alpha-blending/) - [alpha mask](https://learnopencv.com/tag/alpha-mask/) - [alpha matte](https://learnopencv.com/tag/alpha-matte/) - [learning rate](https://learnopencv.com/tag/learning-rate/) - [backpropagation](https://learnopencv.com/tag/backpropagation/) - [gradient descent](https://learnopencv.com/tag/gradient-descent/) - [neural networks](https://learnopencv.com/tag/neural-networks/) - [beginners](https://learnopencv.com/tag/beginners/) - [RGB](https://learnopencv.com/tag/rgb/) - [YCrCb](https://learnopencv.com/tag/ycrcb/) - [HSV](https://learnopencv.com/tag/hsv/) - [cvtColor](https://learnopencv.com/tag/cvtcolor/) - [inRange](https://learnopencv.com/tag/inrange/) - [LAB](https://learnopencv.com/tag/lab/) - [color space](https://learnopencv.com/tag/color-space/) - [hist2d](https://learnopencv.com/tag/hist2d/) - [Windows](https://learnopencv.com/tag/windows/) - [Video](https://learnopencv.com/tag/video/) - [macos](https://learnopencv.com/tag/macos/) - [osx](https://learnopencv.com/tag/osx/) - [sierra](https://learnopencv.com/tag/sierra/) - [el capitan](https://learnopencv.com/tag/el-capitan/) - [ubuntu](https://learnopencv.com/tag/ubuntu/) - [linux](https://learnopencv.com/tag/linux/) - [edge detector](https://learnopencv.com/tag/edge-detector/) - [trackbar](https://learnopencv.com/tag/trackbar/) - [forEach](https://learnopencv.com/tag/foreach/) - [Mat](https://learnopencv.com/tag/mat/) - [OpenCV 3.3.0](https://learnopencv.com/tag/opencv-3-3-0/) - [OpenCV 3.3](https://learnopencv.com/tag/opencv-3-3/) - [Dlib 19.6](https://learnopencv.com/tag/dlib-19-6/) - [Dlib 19.5](https://learnopencv.com/tag/dlib-19-5/) - [Dlib 19.4](https://learnopencv.com/tag/dlib-19-4/) - [deep learning](https://learnopencv.com/tag/deep-learning/) - [tensorflow](https://learnopencv.com/tag/tensorflow/) - [Keras](https://learnopencv.com/tag/keras/) - [PyTorch](https://learnopencv.com/tag/pytorch/) - [CUDA](https://learnopencv.com/tag/cuda/) - [cuDNN](https://learnopencv.com/tag/cudnn/) - [selective search](https://learnopencv.com/tag/selective-search/) - [multilayer perceptron](https://learnopencv.com/tag/multilayer-perceptron/) - [activation function](https://learnopencv.com/tag/activation-function/) - [MNIST](https://learnopencv.com/tag/mnist/) - [hdr](https://learnopencv.com/tag/hdr/) - [computational photography](https://learnopencv.com/tag/computational-photography/) - [tone mapping](https://learnopencv.com/tag/tone-mapping/) - [feedforward neural networks](https://learnopencv.com/tag/feedforward-neural-networks/) - [introduction](https://learnopencv.com/tag/introduction/) - [tutorial](https://learnopencv.com/tag/tutorial/) - [exposure fusion](https://learnopencv.com/tag/exposure-fusion/) - [MergeMertens](https://learnopencv.com/tag/mergemertens/) - [install tensorflow](https://learnopencv.com/tag/install-tensorflow/) - [install pytorch](https://learnopencv.com/tag/install-pytorch/) - [install opencv](https://learnopencv.com/tag/install-opencv/) - [ReLU](https://learnopencv.com/tag/relu/) - [sigmoid](https://learnopencv.com/tag/sigmoid/) - [leaky ReLU](https://learnopencv.com/tag/leaky-relu/) - [Parameteric ReLU](https://learnopencv.com/tag/parameteric-relu/) - [SWISH](https://learnopencv.com/tag/swish/) - [cv4faces](https://learnopencv.com/tag/cv4faces/) - [course](https://learnopencv.com/tag/course/) - [Machine Learning](https://learnopencv.com/tag/machine-learning/) - [Computer Vision](https://learnopencv.com/tag/computer-vision/) - [Image Processing](https://learnopencv.com/tag/image-processing/) - [autoencoder](https://learnopencv.com/tag/autoencoder/) - [denoising](https://learnopencv.com/tag/denoising/) - [character classification](https://learnopencv.com/tag/character-classification/) - [harry potter](https://learnopencv.com/tag/harry-potter/) - [interactive wand](https://learnopencv.com/tag/interactive-wand/) - [dslr](https://learnopencv.com/tag/dslr/) - [exposure](https://learnopencv.com/tag/exposure/) - [ISO](https://learnopencv.com/tag/iso/) - [shutter speed](https://learnopencv.com/tag/shutter-speed/) - [f-stop](https://learnopencv.com/tag/f-stop/) - [aperture size](https://learnopencv.com/tag/aperture-size/) - [depth of field](https://learnopencv.com/tag/depth-of-field/) - [pre-training](https://learnopencv.com/tag/pre-training/) - [transfer learning](https://learnopencv.com/tag/transfer-learning/) - [PCA](https://learnopencv.com/tag/pca/) - [EigenFace](https://learnopencv.com/tag/eigenface/) - [zbar](https://learnopencv.com/tag/zbar/) - [pyzbar](https://learnopencv.com/tag/pyzbar/) - [qrcode](https://learnopencv.com/tag/qrcode/) - [barcode](https://learnopencv.com/tag/barcode/) - [scanner](https://learnopencv.com/tag/scanner/) - [ORB](https://learnopencv.com/tag/orb/) - [findHomography](https://learnopencv.com/tag/findhomography/) - [RANSAC](https://learnopencv.com/tag/ransac/) - [facemark](https://learnopencv.com/tag/facemark/) - [FacemarkAAM](https://learnopencv.com/tag/facemarkaam/) - [FacemarkKazemi](https://learnopencv.com/tag/facemarkkazemi/) - [FacemarkLBF](https://learnopencv.com/tag/facemarklbf/) - [best project award](https://learnopencv.com/tag/best-project-award/) - [hand detector](https://learnopencv.com/tag/hand-detector/) - [virtual makeup](https://learnopencv.com/tag/virtual-makeup/) - [openscan](https://learnopencv.com/tag/openscan/) - [python module](https://learnopencv.com/tag/python-module/) - [openPose](https://learnopencv.com/tag/open-pose/) - [Human Pose Estimation](https://learnopencv.com/tag/human-pose-estimation/) - [tesseract](https://learnopencv.com/tag/tesseract/) - [ocr](https://learnopencv.com/tag/ocr/) - [alexnet](https://learnopencv.com/tag/alexnet/) - [image quality](https://learnopencv.com/tag/image-quality/) - [brisque](https://learnopencv.com/tag/brisque/) - [fifa](https://learnopencv.com/tag/fifa/) - [Digit classification](https://learnopencv.com/tag/digit-classification/) - [LeNet](https://learnopencv.com/tag/lenet/) - [batch normalization](https://learnopencv.com/tag/batch-normalization/) - [classification](https://learnopencv.com/tag/classification/) - [Kernel Trick](https://learnopencv.com/tag/kernel-trick/) - [Radial Basis Function](https://learnopencv.com/tag/radial-basis-function/) - [Moments OpenCV](https://learnopencv.com/tag/moments-opencv/) - [centroid](https://learnopencv.com/tag/centroid/) - [center of shape OpenCV](https://learnopencv.com/tag/center-of-shape-opencv/) - [cv2.moments](https://learnopencv.com/tag/cv2-moments/) - [MOSSE](https://learnopencv.com/tag/mosse/) - [Grid Search](https://learnopencv.com/tag/grid-search/) - [Parameter Tuning](https://learnopencv.com/tag/parameter-tuning/) - [Image Colorization](https://learnopencv.com/tag/image-colorization/) - [video colorization](https://learnopencv.com/tag/video-colorization/) - [CSRT](https://learnopencv.com/tag/csrt/) - [MultiTracker](https://learnopencv.com/tag/multitracker/) - [Jarvis march](https://learnopencv.com/tag/jarvis-march/) - [Graham scan](https://learnopencv.com/tag/graham-scan/) - [Chan's algorithm](https://learnopencv.com/tag/chans-algorithm/) - [findContour](https://learnopencv.com/tag/findcontour/) - [convexHull](https://learnopencv.com/tag/convexhull/) - [drawContour](https://learnopencv.com/tag/drawcontour/) - [Sklansky](https://learnopencv.com/tag/sklansky/) - [Hu Moments](https://learnopencv.com/tag/hu-moments/) - [Moment Invariants](https://learnopencv.com/tag/moment-invariants/) - [Scaling](https://learnopencv.com/tag/scaling/) - [Translation](https://learnopencv.com/tag/translation/) - [Comparison](https://learnopencv.com/tag/comparison/) - [YOLOv3](https://learnopencv.com/tag/yolov3/) - [logo detection](https://learnopencv.com/tag/logo-detection/) - [heatmap](https://learnopencv.com/tag/heatmap/) - [matplotlib](https://learnopencv.com/tag/matplotlib/) - [Docker](https://learnopencv.com/tag/docker/) - [opencv 4.0](https://learnopencv.com/tag/opencv-4-0/) - [Install](https://learnopencv.com/tag/install/) - [OpenCV4](https://learnopencv.com/tag/opencv4/) - [AI](https://learnopencv.com/tag/ai/) - [Segmentation](https://learnopencv.com/tag/segmentation/) - [image segmentation](https://learnopencv.com/tag/image-segmentation/) - [semantic segmentation](https://learnopencv.com/tag/semantic-segmentation/) - [instance segmentation](https://learnopencv.com/tag/instance-segmentation/) - [panoptic segmentation](https://learnopencv.com/tag/panoptic-segmentation/) - [Face detection](https://learnopencv.com/tag/face-detection/) - [OpenCV3](https://learnopencv.com/tag/opencv3/) - [coin identification](https://learnopencv.com/tag/coin-identification/) - [coin counter](https://learnopencv.com/tag/coin-counter/) - [face clustering](https://learnopencv.com/tag/face-clustering/) - [face recognition](https://learnopencv.com/tag/face-recognition/) - [Natural Language Processing](https://learnopencv.com/tag/natural-language-processing/) - [Sentence Encoder](https://learnopencv.com/tag/sentence-encoder/) - [Universal Sentence Encoder](https://learnopencv.com/tag/universal-sentence-encoder/) - [installation](https://learnopencv.com/tag/installation/) - [bash](https://learnopencv.com/tag/bash/) - [OpenCV 3.4.4](https://learnopencv.com/tag/opencv-3-4-4/) - [Batch](https://learnopencv.com/tag/batch/) - [Encoder](https://learnopencv.com/tag/encoder/) - [NLP](https://learnopencv.com/tag/nlp/) - [TensorflowHub](https://learnopencv.com/tag/tensorflowhub/) - [Quora](https://learnopencv.com/tag/quora/) - [Kaggle](https://learnopencv.com/tag/kaggle/) - [opencv 3.4.3](https://learnopencv.com/tag/opencv-3-4-3/) - [ubuntu 16.04](https://learnopencv.com/tag/ubuntu-16-04/) - [ubuntu 18.04](https://learnopencv.com/tag/ubuntu-18-04/) - [Red Hat](https://learnopencv.com/tag/red-hat/) - [CentOS](https://learnopencv.com/tag/centos/) - [moments](https://learnopencv.com/tag/moments/) - [Android](https://learnopencv.com/tag/android/) - [Optimized](https://learnopencv.com/tag/optimized/) - [Small Library Size](https://learnopencv.com/tag/small-library-size/) - [OpenVINO](https://learnopencv.com/tag/openvino/) - [Performance Analysis](https://learnopencv.com/tag/performance-analysis/) - [Pose Estimation](https://learnopencv.com/tag/pose-estimation/) - [YOLO](https://learnopencv.com/tag/yolo/) - [object detector](https://learnopencv.com/tag/object-detector/) - [Video Stabilization](https://learnopencv.com/tag/video-stabilization/) - [Point Feature Matching](https://learnopencv.com/tag/point-feature-matching/) - [Optical Flow](https://learnopencv.com/tag/optical-flow/) - [wrnch](https://learnopencv.com/tag/wrnch/) - [train](https://learnopencv.com/tag/train/) - [Open Images](https://learnopencv.com/tag/open-images/) - [dataset](https://learnopencv.com/tag/dataset/) - [download](https://learnopencv.com/tag/download/) - [Xeus-Cling](https://learnopencv.com/tag/xeus-cling/) - [Jupyter Notebook](https://learnopencv.com/tag/jupyter-notebook/) - [hough transform](https://learnopencv.com/tag/hough-transform/) - [hough line transform](https://learnopencv.com/tag/hough-line-transform/) - [hough circle transform](https://learnopencv.com/tag/hough-circle-transform/) - [line detection](https://learnopencv.com/tag/line-detection/) - [circle detection](https://learnopencv.com/tag/circle-detection/) - [HoughLinesP](https://learnopencv.com/tag/houghlinesp/) - [HoughLines](https://learnopencv.com/tag/houghlines/) - [HoughCircles](https://learnopencv.com/tag/houghcircles/) - [inpainting](https://learnopencv.com/tag/inpainting/) - [INPAINT_NS](https://learnopencv.com/tag/inpaint_ns/) - [INPAINT_TELEA](https://learnopencv.com/tag/inpaint_telea/) - [Hangman](https://learnopencv.com/tag/hangman/) - [project](https://learnopencv.com/tag/project/) - [kickstarter](https://learnopencv.com/tag/kickstarter/) - [tensor](https://learnopencv.com/tag/tensor/) - [libtorch](https://learnopencv.com/tag/libtorch/) - [tensors](https://learnopencv.com/tag/tensors/) - [TorchVision](https://learnopencv.com/tag/torchvision/) - [Resnet](https://learnopencv.com/tag/resnet/) - [artificial intelligence](https://learnopencv.com/tag/artificial-intelligence/) - [DeepLab v3](https://learnopencv.com/tag/deeplab-v3/) - [Fully Convolutional Network (FCN)](https://learnopencv.com/tag/fully-convolutional-network-fcn/) - [EfficientNet](https://learnopencv.com/tag/efficientnet/) - [background estimation](https://learnopencv.com/tag/background-estimation/) - [median filtering](https://learnopencv.com/tag/median-filtering/) - [video analysis](https://learnopencv.com/tag/video-analysis/) - [gaze estimation](https://learnopencv.com/tag/gaze-estimation/) - [gaze tracking](https://learnopencv.com/tag/gaze-tracking/) - [eye tracking](https://learnopencv.com/tag/eye-tracking/) - [reproducibility](https://learnopencv.com/tag/reproducibility/) - [determinism](https://learnopencv.com/tag/determinism/) - [random seed](https://learnopencv.com/tag/random-seed/) - [Camera Calibration](https://learnopencv.com/tag/camera-calibration/) - [Image formation](https://learnopencv.com/tag/image-formation/) - [Camera Matrix](https://learnopencv.com/tag/camera-matrix/) - [Projection Matrix](https://learnopencv.com/tag/projection-matrix/) - [Intrinsic Matrix](https://learnopencv.com/tag/intrinsic-matrix/) - [Extrinsic Matrix](https://learnopencv.com/tag/extrinsic-matrix/) - [calibrateCamera](https://learnopencv.com/tag/calibratecamera/) - [findChessboardCorners](https://learnopencv.com/tag/findchessboardcorners/) - [sfm](https://learnopencv.com/tag/sfm/) - [structure from motion](https://learnopencv.com/tag/structure-from-motion/) - [fully convolutional](https://learnopencv.com/tag/fully-convolutional/) - [resnet18](https://learnopencv.com/tag/resnet18/) - [aruco marker](https://learnopencv.com/tag/aruco-marker/) - [augmented reality](https://learnopencv.com/tag/augmented-reality/) - [receptive field](https://learnopencv.com/tag/receptive-field/) - [image](https://learnopencv.com/tag/image/) - [resnext50](https://learnopencv.com/tag/resnext50/) - [tagging](https://learnopencv.com/tag/tagging/) - [multi-label](https://learnopencv.com/tag/multi-label/) - [NUS-WIDE](https://learnopencv.com/tag/nus-wide/) - [BCE](https://learnopencv.com/tag/bce/) - [MLIC](https://learnopencv.com/tag/mlic/) - [funny mirror](https://learnopencv.com/tag/funny-mirror/) - [virtual camera](https://learnopencv.com/tag/virtual-camera/) - [Lightning](https://learnopencv.com/tag/lightning/) - [federated learning](https://learnopencv.com/tag/federated-learning/) - [pysyft](https://learnopencv.com/tag/pysyft/) - [privacy preserving](https://learnopencv.com/tag/privacy-preserving/) - [ONNX](https://learnopencv.com/tag/onnx/) - [resnet50](https://learnopencv.com/tag/resnet50/) - [pytorch2keras](https://learnopencv.com/tag/pytorch2keras/) - [response map](https://learnopencv.com/tag/response-map/) - [preprocess unit](https://learnopencv.com/tag/preprocess-unit/) - [imageNet](https://learnopencv.com/tag/imagenet/) - [max activation](https://learnopencv.com/tag/max-activation/) - [GCN](https://learnopencv.com/tag/gcn/) - [tensorboard](https://learnopencv.com/tag/tensorboard/) - [logging](https://learnopencv.com/tag/logging/) - [visualisation](https://learnopencv.com/tag/visualisation/) - [graphs](https://learnopencv.com/tag/graphs/) - [experiment management](https://learnopencv.com/tag/experiment-management/) - [experiment logging](https://learnopencv.com/tag/experiment-logging/) - [tools](https://learnopencv.com/tag/tools/) - [weights and biases](https://learnopencv.com/tag/weights-and-biases/) - [thresholding](https://learnopencv.com/tag/thresholding/) - [Otsu](https://learnopencv.com/tag/otsu/) - [Binarization](https://learnopencv.com/tag/binarization/) - [Global threshold](https://learnopencv.com/tag/global-threshold/) - [within-classes variance](https://learnopencv.com/tag/within-classes-variance/) - [foreground separation](https://learnopencv.com/tag/foreground-separation/) - [TensorRT](https://learnopencv.com/tag/tensorrt/) - [zero shot learning](https://learnopencv.com/tag/zero-shot-learning/) - [VGG16](https://learnopencv.com/tag/vgg16/) - [Fine-tuning](https://learnopencv.com/tag/fine-tuning/) - [pillow](https://learnopencv.com/tag/pillow/) - [pillow-simd](https://learnopencv.com/tag/pillow-simd/) - [turbojpeg](https://learnopencv.com/tag/turbojpeg/) - [lmdb](https://learnopencv.com/tag/lmdb/) - [tfrecords](https://learnopencv.com/tag/tfrecords/) - [Image Matting](https://learnopencv.com/tag/image-matting/) - [netron](https://learnopencv.com/tag/netron/) - [Coreml](https://learnopencv.com/tag/coreml/) - [Background Subtraction](https://learnopencv.com/tag/background-subtraction/) - [BGS](https://learnopencv.com/tag/bgs/) - [BGSLibrary](https://learnopencv.com/tag/bgslibrary/) - [SuBSENSE](https://learnopencv.com/tag/subsense/) - [Data Preparation](https://learnopencv.com/tag/data-preparation/) - [GPU](https://learnopencv.com/tag/gpu/) - [Farneback Optical Flow](https://learnopencv.com/tag/farneback-optical-flow/) - [Dense Optical Flow](https://learnopencv.com/tag/dense-optical-flow/) - [embeddings](https://learnopencv.com/tag/embeddings/) - [Java](https://learnopencv.com/tag/java/) - [Comet Logger](https://learnopencv.com/tag/comet-logger/) - [Neptune Logger](https://learnopencv.com/tag/neptune-logger/) - [Tensorboard Logger](https://learnopencv.com/tag/tensorboard-logger/) - [HRNet](https://learnopencv.com/tag/hrnet/) - [machine-learning](https://learnopencv.com/tag/machine-learning-3/) - [MRI](https://learnopencv.com/tag/mri/) - [RAFT](https://learnopencv.com/tag/raft/) - [FlowNet](https://learnopencv.com/tag/flownet/) - [SINTEL](https://learnopencv.com/tag/sintel/) - [Lucas Kanade](https://learnopencv.com/tag/lucas-kanade/) - [Sparse Optical Flow](https://learnopencv.com/tag/sparse-optical-flow/) - [Optical Flow theory](https://learnopencv.com/tag/optical-flow-theory/) - [RLOF](https://learnopencv.com/tag/rlof/) - [Autonomous Driving](https://learnopencv.com/tag/autonomous-driving/) - [Depth Estimation](https://learnopencv.com/tag/depth-estimation/) - [Stereo Matching](https://learnopencv.com/tag/stereo-matching/) - [SOTA](https://learnopencv.com/tag/sota/) - [KITTI](https://learnopencv.com/tag/kitti/) - [SceneFlow](https://learnopencv.com/tag/sceneflow/) - [Middlebury](https://learnopencv.com/tag/middlebury/) - [AANet](https://learnopencv.com/tag/aanet/) - [MobileNet](https://learnopencv.com/tag/mobilenet/) - [Android Studio](https://learnopencv.com/tag/android-studio/) - [tricks](https://learnopencv.com/tag/tricks/) - [MRNet Challenge](https://learnopencv.com/tag/mrnet-challenge/) - [Medical Imaging](https://learnopencv.com/tag/medical-imaging/) - [lens distortion](https://learnopencv.com/tag/lens-distortion/) - [fisheye](https://learnopencv.com/tag/fisheye/) - [barrel](https://learnopencv.com/tag/barrel/) - [3d Vision](https://learnopencv.com/tag/3d-vision/) - [OpenCV AI Kit](https://learnopencv.com/tag/opencv-ai-kit/) - [Spatial AI](https://learnopencv.com/tag/spatial-ai/) - [snake game](https://learnopencv.com/tag/snake-game/) - [highgui](https://learnopencv.com/tag/highgui/) - [tetris](https://learnopencv.com/tag/tetris/) - [filtering](https://learnopencv.com/tag/filtering/) - [Image basics](https://learnopencv.com/tag/image-basics/) - [EXE](https://learnopencv.com/tag/exe/) - [Object Localization](https://learnopencv.com/tag/object-localization/) - [CPP](https://learnopencv.com/tag/cpp/) - [installer](https://learnopencv.com/tag/installer/) - [setup](https://learnopencv.com/tag/setup/) - [Visual Studio](https://learnopencv.com/tag/visual-studio/) - [low-light](https://learnopencv.com/tag/low-light/) - [nighttime](https://learnopencv.com/tag/nighttime/) - [low illumination](https://learnopencv.com/tag/low-illumination/) - [dark image](https://learnopencv.com/tag/dark-image/) - [improve lighting](https://learnopencv.com/tag/improve-lighting/) - [Code](https://learnopencv.com/tag/code/) - [Microsoft](https://learnopencv.com/tag/microsoft/) - [Configure](https://learnopencv.com/tag/configure/) - [executable](https://learnopencv.com/tag/executable/) - [epipolar geometry](https://learnopencv.com/tag/epipolar-geometry/) - [stereo computer vision](https://learnopencv.com/tag/stereo-computer-vision/) - [DIY-stereo-camera](https://learnopencv.com/tag/diy-stereo-camera/) - [OAK-D](https://learnopencv.com/tag/oak-d/) - [stereoscopy](https://learnopencv.com/tag/stereoscopy/) - [siamese networks](https://learnopencv.com/tag/siamese-networks/) - [arc face](https://learnopencv.com/tag/arc-face/) - [triplet loss](https://learnopencv.com/tag/triplet-loss-2/) - [Video Classification](https://learnopencv.com/tag/video-classification/) - [Human Activity Recognition](https://learnopencv.com/tag/human-activity-recognition/) - [GPU inference](https://learnopencv.com/tag/gpu-inference/) - [OpenCV DNN](https://learnopencv.com/tag/opencv-dnn/) - [Human Keypoint Detection](https://learnopencv.com/tag/human-keypoint-detection/) - [write video opencv](https://learnopencv.com/tag/write-video-opencv/) - [read video C++](https://learnopencv.com/tag/read-video-c/) - [read video python](https://learnopencv.com/tag/read-video-python/) - [opencv read video](https://learnopencv.com/tag/opencv-read-video/) - [cv2.VideoWriter](https://learnopencv.com/tag/cv2-videowriter/) - [cv2.imread](https://learnopencv.com/tag/cv2-imread/) - [cv2.imwrite](https://learnopencv.com/tag/cv2-imwrite/) - [cv2.VideoCapture](https://learnopencv.com/tag/cv2-videocapture/) - [perspective transform](https://learnopencv.com/tag/perspective-transform/) - [opencv homography](https://learnopencv.com/tag/opencv-homography/) - [corresponding points](https://learnopencv.com/tag/corresponding-points/) - [cv2.warpPerspective](https://learnopencv.com/tag/cv2-warpperspective/) - [cv2.findHomography](https://learnopencv.com/tag/cv2-findhomography/) - [cv2.Sobel](https://learnopencv.com/tag/cv2-sobel/) - [HOG Descriptor](https://learnopencv.com/tag/hog-descriptor/) - [cv2.cartToPolar](https://learnopencv.com/tag/cv2-carttopolar/) - [cv2.SimpleBlobDetector](https://learnopencv.com/tag/cv2-simpleblobdetector/) - [cv2.drawKeypoints](https://learnopencv.com/tag/cv2-drawkeypoints/) - [COCO-keypoints](https://learnopencv.com/tag/coco-keypoints/) - [cv2.minMaxLoc](https://learnopencv.com/tag/cv2-minmaxloc/) - [MPI human pose](https://learnopencv.com/tag/mpi-human-pose/) - [cv2.dnn.readNetFromCaffe](https://learnopencv.com/tag/cv2-dnn-readnetfromcaffe/) - [cv2.dnn.blobFromImage](https://learnopencv.com/tag/cv2-dnn-blobfromimage/) - [cv2.CAP_PROP_FPS](https://learnopencv.com/tag/cv2-cap_prop_fps/) - [video processing](https://learnopencv.com/tag/video-processing/) - [bash script](https://learnopencv.com/tag/bash-script/) - [cmake](https://learnopencv.com/tag/cmake/) - [Raspbian OS](https://learnopencv.com/tag/raspbian-os/) - [FAST](https://learnopencv.com/tag/fast/) - [cv2.DescriptorMatcher_create](https://learnopencv.com/tag/cv2-descriptormatcher_create/) - [cv2.ORB_create](https://learnopencv.com/tag/cv2-orb_create/) - [BRISK](https://learnopencv.com/tag/brisk/) - [cv2.cvtColor](https://learnopencv.com/tag/cv2-cvtcolor/) - [cv2.drawMatches](https://learnopencv.com/tag/cv2-drawmatches/) - [descriptor](https://learnopencv.com/tag/descriptor/) - [cv2.dnn](https://learnopencv.com/tag/cv2-dnn/) - [OpenCV DNN cuda](https://learnopencv.com/tag/opencv-dnn-cuda/) - [OpenCV DNN GPU](https://learnopencv.com/tag/opencv-dnn-gpu/) - [OpenCV DNN cudnn](https://learnopencv.com/tag/opencv-dnn-cudnn/) - [cv2.morphologyEx](https://learnopencv.com/tag/cv2-morphologyex/) - [foreground segmentation](https://learnopencv.com/tag/foreground-segmentation/) - [cv2.bitwise_and](https://learnopencv.com/tag/cv2-bitwise_and/) - [color based segementation](https://learnopencv.com/tag/color-based-segementation/) - [cv2.addWeighted](https://learnopencv.com/tag/cv2-addweighted/) - [cv2.bitwise_not](https://learnopencv.com/tag/cv2-bitwise_not/) - [recognition model](https://learnopencv.com/tag/recognition-model/) - [activity classification](https://learnopencv.com/tag/activity-classification/) - [classification problems](https://learnopencv.com/tag/classification-problems/) - [image enhancement](https://learnopencv.com/tag/image-enhancement/) - [dual channel prior](https://learnopencv.com/tag/dual-channel-prior/) - [transmission maps](https://learnopencv.com/tag/transmission-maps/) - [guided filter](https://learnopencv.com/tag/guided-filter/) - [Install OpenCV EXE](https://learnopencv.com/tag/install-opencv-exe/) - [ESPCN](https://learnopencv.com/tag/espcn/) - [SuperResolution](https://learnopencv.com/tag/superresolution/) - [LapSRN](https://learnopencv.com/tag/lapsrn/) - [FSRCNN](https://learnopencv.com/tag/fsrcnn/) - [OpenCV-DNN](https://learnopencv.com/tag/opencv-dnn-2/) - [cv2.dnn_superres](https://learnopencv.com/tag/cv2-dnn_superres/) - [bicubic](https://learnopencv.com/tag/bicubic/) - [EDSR](https://learnopencv.com/tag/edsr/) - [cv2.findContours](https://learnopencv.com/tag/cv2-findcontours/) - [cv2.drawContours](https://learnopencv.com/tag/cv2-drawcontours/) - [Contours](https://learnopencv.com/tag/contours/) - [Binary Thresholding](https://learnopencv.com/tag/binary-thresholding/) - [cv2.CHAIN APPROX NONE](https://learnopencv.com/tag/cv2-chain-approx-none/) - [cv2.CHAIN APPROX SIMPLE](https://learnopencv.com/tag/cv2-chain-approx-simple/) - [cv2.threshold](https://learnopencv.com/tag/cv2-threshold/) - [findContours](https://learnopencv.com/tag/findcontours/) - [depthEstimation](https://learnopencv.com/tag/depthestimation/) - [disparityMap](https://learnopencv.com/tag/disparitymap/) - [obstacleAvoidance](https://learnopencv.com/tag/obstacleavoidance/) - [sumOfAbsoluteDifference](https://learnopencv.com/tag/sumofabsolutedifference/) - [spatialAIseries](https://learnopencv.com/tag/spatialaiseries/) - [stereoCamera](https://learnopencv.com/tag/stereocamera/) - [dynamicProgramming](https://learnopencv.com/tag/dynamicprogramming/) - [blockMatchingAlgorithm](https://learnopencv.com/tag/blockmatchingalgorithm/) - [cv2.boundingRect](https://learnopencv.com/tag/cv2-boundingrect/) - [openCV-AI-Kit](https://learnopencv.com/tag/opencv-ai-kit-2/) - [denseStereoCorrespondence](https://learnopencv.com/tag/densestereocorrespondence/) - [cv2.StereoBM](https://learnopencv.com/tag/cv2-stereobm/) - [cv2.imshow](https://learnopencv.com/tag/cv2-imshow/) - [imwrite](https://learnopencv.com/tag/imwrite/) - [imshow](https://learnopencv.com/tag/imshow/) - [digital image processing](https://learnopencv.com/tag/digital-image-processing/) - [imageClassification](https://learnopencv.com/tag/imageclassification/) - [objectDetection](https://learnopencv.com/tag/objectdetection/) - [functionalities](https://learnopencv.com/tag/functionalities/) - [msCoco](https://learnopencv.com/tag/mscoco/) - [caffe](https://learnopencv.com/tag/caffe/) - [framework](https://learnopencv.com/tag/framework/) - [models](https://learnopencv.com/tag/models/) - [torch](https://learnopencv.com/tag/torch/) - [boundingBox](https://learnopencv.com/tag/boundingbox/) - [cv2.rectangle](https://learnopencv.com/tag/cv2-rectangle/) - [darknet](https://learnopencv.com/tag/darknet/) - [blobFromImage](https://learnopencv.com/tag/blobfromimage/) - [denseNet121](https://learnopencv.com/tag/densenet121/) - [dataCompression](https://learnopencv.com/tag/datacompression/) - [googleCartoonDataset](https://learnopencv.com/tag/googlecartoondataset/) - [fashionMnist](https://learnopencv.com/tag/fashionmnist/) - [decoder](https://learnopencv.com/tag/decoder/) - [conv2D](https://learnopencv.com/tag/conv2d/) - [imageReconstruction](https://learnopencv.com/tag/imagereconstruction/) - [latentSpace](https://learnopencv.com/tag/latentspace/) - [neuralNetwork](https://learnopencv.com/tag/neuralnetwork/) - [variational autoencoder](https://learnopencv.com/tag/variational-autoencoder/) - [generative modeling](https://learnopencv.com/tag/generative-modeling/) - [Tensorflow 2](https://learnopencv.com/tag/tensorflow-2/) - [imageGeneration](https://learnopencv.com/tag/imagegeneration/) - [tf.keras](https://learnopencv.com/tag/tf-keras/) - [normal distribution](https://learnopencv.com/tag/normal-distribution/) - [reparameterization](https://learnopencv.com/tag/reparameterization/) - [cv.dnn.blobFromImage](https://learnopencv.com/tag/cv-dnn-blobfromimage/) - [cv.dnn](https://learnopencv.com/tag/cv-dnn/) - [inference](https://learnopencv.com/tag/inference/) - [nmsThreshold](https://learnopencv.com/tag/nmsthreshold/) - [non-maximumSuppression](https://learnopencv.com/tag/non-maximumsuppression/) - [DNN_BACKEND_OPENCV](https://learnopencv.com/tag/dnn_backend_opencv/) - [performanceAnalysis](https://learnopencv.com/tag/performanceanalysis/) - [NMSBoxes](https://learnopencv.com/tag/nmsboxes/) - [readNetFromDarknet](https://learnopencv.com/tag/readnetfromdarknet/) - [cv.dnn.NMSBoxes](https://learnopencv.com/tag/cv-dnn-nmsboxes/) - [cv.dnn.DNN_BACKEND_OPENCV](https://learnopencv.com/tag/cv-dnn-dnn_backend_opencv/) - [cv.dnn.readNetFromDarknet](https://learnopencv.com/tag/cv-dnn-readnetfromdarknet/) - [dnnFaceDetector](https://learnopencv.com/tag/dnnfacedetector/) - [dlib.cnn_face_detection_model_v1](https://learnopencv.com/tag/dlib-cnn_face_detection_model_v1/) - [mmodFaceDetector](https://learnopencv.com/tag/mmodfacedetector/) - [hogFaceDetector](https://learnopencv.com/tag/hogfacedetector/) - [dlib.get_frontal_face_detector](https://learnopencv.com/tag/dlib-get_frontal_face_detector/) - [performanceComparision](https://learnopencv.com/tag/performancecomparision/) - [cv2.CascadeClassifier](https://learnopencv.com/tag/cv2-cascadeclassifier/) - [readNetFromTensorflow](https://learnopencv.com/tag/readnetfromtensorflow/) - [evaluation](https://learnopencv.com/tag/evaluation/) - [cascadeClassifier](https://learnopencv.com/tag/cascade-classifier/) - [readNetFromCaffe](https://learnopencv.com/tag/readnetfromcaffe/) - [faceDetector](https://learnopencv.com/tag/facedetector/) - [cv2.dnn.readNetFromTensorflow](https://learnopencv.com/tag/cv2-dnn-readnetfromtensorflow/) - [haarCascade](https://learnopencv.com/tag/haarcascade/) - [agePrediction](https://learnopencv.com/tag/ageprediction/) - [dnn.readNet](https://learnopencv.com/tag/dnn-readnet/) - [dnn.blobFromImage](https://learnopencv.com/tag/dnn-blobfromimage/) - [cv.dnn.readNet](https://learnopencv.com/tag/cv-dnn-readnet/) - [genderPrediction](https://learnopencv.com/tag/genderprediction/) - [confusionMatrix](https://learnopencv.com/tag/confusionmatrix/) - [faceDetection](https://learnopencv.com/tag/facedetection/) - [humanPoseEstimation](https://learnopencv.com/tag/humanposeestimation/) - [handDetector](https://learnopencv.com/tag/handdetector/) - [keypointDetection](https://learnopencv.com/tag/keypointdetection/) - [deepLearning](https://learnopencv.com/tag/deeplearning/) - [poseEstimation](https://learnopencv.com/tag/poseestimation/) - [confidenceMaps](https://learnopencv.com/tag/confidencemaps/) - [affinityHeatmaps](https://learnopencv.com/tag/affinityheatmaps/) - [cv2.GaussianBlur](https://learnopencv.com/tag/cv2-gaussianblur/) - [addWeighted](https://learnopencv.com/tag/addweighted/) - [gaussianBlur](https://learnopencv.com/tag/gaussianblur/) - [personWiseKeypoints](https://learnopencv.com/tag/personwisekeypoints/) - [cv2.fillConvexPoly](https://learnopencv.com/tag/cv2-fillconvexpoly/) - [partAffinityMaps](https://learnopencv.com/tag/partaffinitymaps/) - [coco](https://learnopencv.com/tag/coco/) - [maskRcnn](https://learnopencv.com/tag/maskrcnn/) - [DNN_TARGET_CPU](https://learnopencv.com/tag/dnn_target_cpu/) - [cv.dnn.DNN_TARGET_CPU](https://learnopencv.com/tag/cv-dnn-dnn_target_cpu/) - [DNN_TARGET_OPENCL](https://learnopencv.com/tag/dnn_target_opencl/) - [cv.dnn.DNN_TARGET_OPENCL](https://learnopencv.com/tag/cv-dnn-dnn_target_opencl/) - [cv.dnn.readNetFromTensorflow](https://learnopencv.com/tag/cv-dnn-readnetfromtensorflow/) - [textDetection](https://learnopencv.com/tag/textdetection/) - [readNet](https://learnopencv.com/tag/readnet/) - [torch.no_grad](https://learnopencv.com/tag/torch-no_grad/) - [wrapPerspective](https://learnopencv.com/tag/wrapperspective/) - [torch.Tensor](https://learnopencv.com/tag/torch-tensor/) - [facialLandmarkDetection](https://learnopencv.com/tag/faciallandmarkdetection/) - [colorRebalancing](https://learnopencv.com/tag/colorrebalancing/) - [cv.dnn.readNetFromCaffe](https://learnopencv.com/tag/cv-dnn-readnetfromcaffe/) - [imageColorization](https://learnopencv.com/tag/imagecolorization/) - [cv.cvtColor](https://learnopencv.com/tag/cv-cvtcolor/) - [convolutionalneuralNetwork](https://learnopencv.com/tag/convolutionalneuralnetwork/) - [cv2.dnn.DNN_BACKEND_INFERENCE_ENGINE](https://learnopencv.com/tag/cv2-dnn-dnn_backend_inference_engine/) - [DNN_BACKEND_INFERENCE_ENGINE](https://learnopencv.com/tag/dnn_backend_inference_engine/) - [objectDetector](https://learnopencv.com/tag/objectdetector/) - [cv2.dnn.DNN_TARGET_CPU](https://learnopencv.com/tag/cv2-dnn-dnn_target_cpu/) - [cv2.dnn.DNN_BACKEND_OPENCV](https://learnopencv.com/tag/cv2-dnn-dnn_backend_opencv/) - [readNetFromONNX](https://learnopencv.com/tag/readnetfromonnx/) - [cv2.dnn.readNetFromONNX](https://learnopencv.com/tag/cv2-dnn-readnetfromonnx/) - [API](https://learnopencv.com/tag/api/) - [DNN_TARGET_CUDA](https://learnopencv.com/tag/dnn_target_cuda/) - [DNN_BACKEND_CUDA](https://learnopencv.com/tag/dnn_backend_cuda/) - [DNN_Module](https://learnopencv.com/tag/dnn_module/) - [GPU_Inference](https://learnopencv.com/tag/gpu_inference/) - [CPU](https://learnopencv.com/tag/cpu/) - [neuralNetworks](https://learnopencv.com/tag/neuralnetworks/) - [playing dino](https://learnopencv.com/tag/playing-dino/) - [pyautoGUI](https://learnopencv.com/tag/pyautogui/) - [human computer interaction](https://learnopencv.com/tag/human-computer-interaction/) - [VGGNet](https://learnopencv.com/tag/vggnet/) - [generativeModels](https://learnopencv.com/tag/generativemodels/) - [kNN](https://learnopencv.com/tag/knn/) - [supervisedLearning](https://learnopencv.com/tag/supervisedlearning/) - [unsupervisedLearning](https://learnopencv.com/tag/unsupervisedlearning/) - [LogisticRegression](https://learnopencv.com/tag/logisticregression/) - [decisionTree](https://learnopencv.com/tag/decisiontree/) - [machineLearning](https://learnopencv.com/tag/machinelearning/) - [discriminativeModels](https://learnopencv.com/tag/discriminativemodels/) - [DecisionTreeClassifier](https://learnopencv.com/tag/decisiontreeclassifier/) - [RandomForestClassifier](https://learnopencv.com/tag/randomforestclassifier/) - [RandomForest](https://learnopencv.com/tag/randomforest/) - [computerVision](https://learnopencv.com/tag/computervision/) - [how-to](https://learnopencv.com/tag/how-to-2/) - [multi-task learning](https://learnopencv.com/tag/multi-task-learning/) - [cv2.resize](https://learnopencv.com/tag/cv2-resize/) - [resize](https://learnopencv.com/tag/resize/) - [interpolation](https://learnopencv.com/tag/interpolation/) - [cv2.INTER_LINEAR](https://learnopencv.com/tag/cv2-inter_linear/) - [cv2.INTER_AREA](https://learnopencv.com/tag/cv2-inter_area/) - [cv2.INTER_NEAREST](https://learnopencv.com/tag/cv2-inter_nearest/) - [cv2.INTER_CUBIC](https://learnopencv.com/tag/cv2-inter_cubic/) - [image crop](https://learnopencv.com/tag/image-crop/) - [patches](https://learnopencv.com/tag/patches/) - [image patches](https://learnopencv.com/tag/image-patches/) - [architecture](https://learnopencv.com/tag/architecture/) - [getRotationMatrix2D](https://learnopencv.com/tag/getrotationmatrix2d/) - [cv2.getRotationMatrix2D](https://learnopencv.com/tag/cv2-getrotationmatrix2d/) - [cv2.warpAffine](https://learnopencv.com/tag/cv2-warpaffine/) - [image translation](https://learnopencv.com/tag/image-translation/) - [image rotation](https://learnopencv.com/tag/image-rotation/) - [cv2.line](https://learnopencv.com/tag/cv2-line/) - [cv2.circle](https://learnopencv.com/tag/cv2-circle/) - [cv2.ellipse](https://learnopencv.com/tag/cv2-ellipse/) - [cv2.putText](https://learnopencv.com/tag/cv2-puttext/) - [line](https://learnopencv.com/tag/line/) - [putText](https://learnopencv.com/tag/puttext/) - [rectangle](https://learnopencv.com/tag/rectangle/) - [ellipse](https://learnopencv.com/tag/ellipse/) - [circle](https://learnopencv.com/tag/circle/) - [nms](https://learnopencv.com/tag/nms/) - [IoU](https://learnopencv.com/tag/iou/) - [Intersection over Union](https://learnopencv.com/tag/intersection-over-union/) - [Non Maximum Suppression](https://learnopencv.com/tag/non-maximum-suppression/) - [opencvBuiltInBlur](https://learnopencv.com/tag/opencvbuiltinblur/) - [identityKernel](https://learnopencv.com/tag/identitykernel/) - [filter2D](https://learnopencv.com/tag/filter2d/) - [cv2.filter2D](https://learnopencv.com/tag/cv2-filter2d/) - [sharpen](https://learnopencv.com/tag/sharpen/) - [ksize](https://learnopencv.com/tag/ksize/) - [cv2.bilateralFilter](https://learnopencv.com/tag/cv2-bilateralfilter/) - [blur](https://learnopencv.com/tag/blur/) - [convolutionKernels](https://learnopencv.com/tag/convolutionkernels/) - [bilateralFilter](https://learnopencv.com/tag/bilateralfilter/) - [2D-convolutionKernels](https://learnopencv.com/tag/2d-convolutionkernels/) - [cv2.medianBlur](https://learnopencv.com/tag/cv2-medianblur/) - [medianBlur](https://learnopencv.com/tag/medianblur/) - [THRESH_TOZERO](https://learnopencv.com/tag/thresh_tozero/) - [THRESH_TRUNC](https://learnopencv.com/tag/thresh_trunc/) - [THRESH_BINARY_INV](https://learnopencv.com/tag/thresh_binary_inv/) - [THRESH_TOZERO_INV](https://learnopencv.com/tag/thresh_tozero_inv/) - [edge detection](https://learnopencv.com/tag/edge-detection/) - [cv2.Canny](https://learnopencv.com/tag/cv2-canny/) - [Sobel](https://learnopencv.com/tag/sobel/) - [Canny](https://learnopencv.com/tag/canny/) - [OpenCV GUI](https://learnopencv.com/tag/opencv-gui/) - [cv2.setMouseCallback](https://learnopencv.com/tag/cv2-setmousecallback/) - [setMouseCallback](https://learnopencv.com/tag/setmousecallback/) - [cv2.createTrackbar](https://learnopencv.com/tag/cv2-createtrackbar/) - [createTrackbar](https://learnopencv.com/tag/createtrackbar/) - [GANs](https://learnopencv.com/tag/gans/) - [tensorflow.keras](https://learnopencv.com/tag/tensorflow-keras/) - [torch.nn](https://learnopencv.com/tag/torch-nn/) - [DCGAN](https://learnopencv.com/tag/dcgan/) - [Pix2Pix](https://learnopencv.com/tag/pix2pix/) - [Multi-GPU](https://learnopencv.com/tag/multi-gpu/) - [CGAN](https://learnopencv.com/tag/cgan/) - [UNET](https://learnopencv.com/tag/unet/) - [Human Action Recognition](https://learnopencv.com/tag/human-action-recognition/) - [Detectron2](https://learnopencv.com/tag/detectron2/) - [LSTM](https://learnopencv.com/tag/lstm/) - [Getting started](https://learnopencv.com/tag/getting-started/) - [Action Recognition](https://learnopencv.com/tag/action-recognition/) - [Driver Action Recognition](https://learnopencv.com/tag/driver-action-recognition/) - [OpenVINO Toolkit](https://learnopencv.com/tag/openvino-toolkit/) - [Model Optimization](https://learnopencv.com/tag/model-optimization/) - [Tiny YOLOv4](https://learnopencv.com/tag/tiny-yolov4/) - [Model Quantization](https://learnopencv.com/tag/model-quantization/) - [FP32](https://learnopencv.com/tag/fp32/) - [INT8](https://learnopencv.com/tag/int8/) - [FP16](https://learnopencv.com/tag/fp16/) - [Intel Integrated GPU](https://learnopencv.com/tag/intel-integrated-gpu/) - [AccuracyAwareQuatization](https://learnopencv.com/tag/accuracyawarequatization/) - [OpenVINO Deep Learning Workbench](https://learnopencv.com/tag/openvino-deep-learning-workbench/) - [3D Computer Vision](https://learnopencv.com/tag/3d-computer-vision/) - [Stereo Disparity Estimation](https://learnopencv.com/tag/stereo-disparity-estimation/) - [Disparity Estimation](https://learnopencv.com/tag/disparity-estimation/) - [PSMNet](https://learnopencv.com/tag/psmnet/) - [Volumetric Disparity Estimation](https://learnopencv.com/tag/volumetric-disparity-estimation/) - [style transfer](https://learnopencv.com/tag/style-transfer/) - [modelplace.ai](https://learnopencv.com/tag/modelplace-ai/) - [benchmarking](https://learnopencv.com/tag/benchmarking/) - [Text To Speech](https://learnopencv.com/tag/text-to-speech/) - [Lip Sync](https://learnopencv.com/tag/lip-sync/) - [QR Code](https://learnopencv.com/tag/qr-code/) - [Wechat](https://learnopencv.com/tag/wechat/) - [OpenCV AI Kit with Depth](https://learnopencv.com/tag/opencv-ai-kit-with-depth/) - [OAK-D OAK-D Lite Spatial AI DepthAI Stereo Vision EDGE AI Pipeline Node](https://learnopencv.com/tag/oak-d-oak-d-lite-spatial-ai-depthai-stereo-vision-edge-ai-pipeline-node/) - [OAK-D Lite](https://learnopencv.com/tag/oak-d-lite/) - [DepthAI](https://learnopencv.com/tag/depthai/) - [Stereo Vision](https://learnopencv.com/tag/stereo-vision/) - [EDGE AI](https://learnopencv.com/tag/edge-ai/) - [Pipeline](https://learnopencv.com/tag/pipeline/) - [Node](https://learnopencv.com/tag/node/) - [Depth Estimation Pipeline](https://learnopencv.com/tag/depth-estimation-pipeline/) - [Disparity](https://learnopencv.com/tag/disparity/) - [Stereo vision geometry](https://learnopencv.com/tag/stereo-vision-geometry/) - [Binocular vision](https://learnopencv.com/tag/binocular-vision/) - [Baseline](https://learnopencv.com/tag/baseline/) - [Stereo rectification](https://learnopencv.com/tag/stereo-rectification/) - [Pretraining](https://learnopencv.com/tag/pretraining/) - [Fine Tuning](https://learnopencv.com/tag/fine-tuning-2/) - [CheXpert](https://learnopencv.com/tag/chexpert/) - [X-Ray](https://learnopencv.com/tag/x-ray/) - [OCT](https://learnopencv.com/tag/oct/) - [Endoscopy](https://learnopencv.com/tag/endoscopy/) - [Fundus](https://learnopencv.com/tag/fundus/) - [RetinaNet](https://learnopencv.com/tag/retinanet/) - [Scanning Electron Microscope](https://learnopencv.com/tag/scanning-electron-microscope/) - [Ensemble Model](https://learnopencv.com/tag/ensemble-model/) - [Climate Change](https://learnopencv.com/tag/climate-change/) - [TACO Dataset](https://learnopencv.com/tag/taco-dataset/) - [Plastic Bottle Detection](https://learnopencv.com/tag/plastic-bottle-detection/) - [Image Scraper](https://learnopencv.com/tag/image-scraper/) - [Jupyter Bbox Widget](https://learnopencv.com/tag/jupyter-bbox-widget/) - [imageAI](https://learnopencv.com/tag/imageai/) - [YOLO v3](https://learnopencv.com/tag/yolo-v3/) - [Graph neural network](https://learnopencv.com/tag/graph-neural-network/) - [Multi-attribute object detection](https://learnopencv.com/tag/multi-attribute-object-detection/) - [Model Zoo](https://learnopencv.com/tag/model-zoo/) - [Machine Learning Models](https://learnopencv.com/tag/machine-learning-models/) - [ML Models](https://learnopencv.com/tag/ml-models/) - [Jetson Model Zoo](https://learnopencv.com/tag/jetson-model-zoo/) - [mediapipe](https://learnopencv.com/tag/mediapipe/) - [ONNX models](https://learnopencv.com/tag/onnx-models/) - [OpenCV Feature Matching](https://learnopencv.com/tag/opencv-feature-matching/) - [Chrome Dino Game Bot](https://learnopencv.com/tag/chrome-dino-game-bot/) - [Contour analysis](https://learnopencv.com/tag/contour-analysis/) - [MSS screen capture](https://learnopencv.com/tag/mss-screen-capture/) - [BRIEF AutoPyGUI](https://learnopencv.com/tag/brief-autopygui/) - [MediaPipe Solutions](https://learnopencv.com/tag/mediapipe-solutions/) - [MediaPipe Toolkit](https://learnopencv.com/tag/mediapipe-toolkit/) - [MediaPipe Pose](https://learnopencv.com/tag/mediapipe-pose/) - [ANPR](https://learnopencv.com/tag/anpr/) - [YOLOv4](https://learnopencv.com/tag/yolov4/) - [GTC](https://learnopencv.com/tag/gtc/) - [GTC22](https://learnopencv.com/tag/gtc22/) - [3D Deep Learning](https://learnopencv.com/tag/3d-deep-learning/) - [Kaolin](https://learnopencv.com/tag/kaolin/) - [Hopper H100 GPU](https://learnopencv.com/tag/hopper-h100-gpu/) - [HP100](https://learnopencv.com/tag/hp100/) - [Hopper](https://learnopencv.com/tag/hopper/) - [3080 Ti](https://learnopencv.com/tag/3080-ti/) - [3008 Ti](https://learnopencv.com/tag/3008-ti/) - [safety](https://learnopencv.com/tag/safety/) - [AUTOSAR](https://learnopencv.com/tag/autosar/) - [products](https://learnopencv.com/tag/products/) - [MISRA](https://learnopencv.com/tag/misra/) - [automotive](https://learnopencv.com/tag/automotive/) - [Augmented Reality Filters](https://learnopencv.com/tag/augmented-reality-filters/) - [AR](https://learnopencv.com/tag/ar/) - [Instagram Filters](https://learnopencv.com/tag/instagram-filters/) - [Snapchat Filters](https://learnopencv.com/tag/snapchat-filters/) - [YOLOv5 c++](https://learnopencv.com/tag/yolov5-c/) - [YOLOv5 Python](https://learnopencv.com/tag/yolov5-python/) - [YOLOv5](https://learnopencv.com/tag/yolov5/) - [Object Detection Training](https://learnopencv.com/tag/object-detection-training/) - [OAK](https://learnopencv.com/tag/oak/) - [Pretrained Model](https://learnopencv.com/tag/pretrained-model/) - [UINT-8](https://learnopencv.com/tag/uint-8/) - [FP-16](https://learnopencv.com/tag/fp-16/) - [Edge Inference](https://learnopencv.com/tag/edge-inference/) - [Post Training Quantization](https://learnopencv.com/tag/post-training-quantization/) - [TensorFlow Lite](https://learnopencv.com/tag/tensorflow-lite/) - [TensorFlow Lite Model Maker](https://learnopencv.com/tag/tensorflow-lite-model-maker/) - [Landmark Detection](https://learnopencv.com/tag/landmark-detection/) - [Depth Map](https://learnopencv.com/tag/depth-map/) - [Anti-Spoofing](https://learnopencv.com/tag/anti-spoofing/) - [Depth Sensor](https://learnopencv.com/tag/depth-sensor/) - [Face Authentication](https://learnopencv.com/tag/face-authentication/) - [Spoofing](https://learnopencv.com/tag/spoofing/) - [SphereFace](https://learnopencv.com/tag/sphereface/) - [gestures](https://learnopencv.com/tag/gestures/) - [v4l2loopback](https://learnopencv.com/tag/v4l2loopback/) - [zoom](https://learnopencv.com/tag/zoom/) - [DeepSORT](https://learnopencv.com/tag/deepsort/) - [Tracking](https://learnopencv.com/tag/tracking/) - [SORT](https://learnopencv.com/tag/sort/) - [Multi Object Tacker](https://learnopencv.com/tag/multi-object-tacker/) - [ClearMOT](https://learnopencv.com/tag/clearmot/) - [Model Evaluation Metrics](https://learnopencv.com/tag/model-evaluation-metrics/) - [MAP](https://learnopencv.com/tag/map/) - [AP](https://learnopencv.com/tag/ap/) - [GPU architectures](https://learnopencv.com/tag/gpu-architectures/) - [Turing](https://learnopencv.com/tag/turing/) - [Ampere](https://learnopencv.com/tag/ampere/) - [VOLTA](https://learnopencv.com/tag/volta/) - [TESLA](https://learnopencv.com/tag/tesla/) - [PASCAL](https://learnopencv.com/tag/pascal/) - [Grabcut](https://learnopencv.com/tag/grabcut/) - [Scanning](https://learnopencv.com/tag/scanning/) - [Document scanner](https://learnopencv.com/tag/document-scanner/) - [posture detection](https://learnopencv.com/tag/posture-detection/) - [body posture detection](https://learnopencv.com/tag/body-posture-detection/) - [YOLOv5 github](https://learnopencv.com/tag/yolov5-github/) - [YOLOv5 Ultralytics](https://learnopencv.com/tag/yolov5-ultralytics/) - [yolov7 paper](https://learnopencv.com/tag/yolov7-paper/) - [yolov7 inference](https://learnopencv.com/tag/yolov7-inference/) - [yolov7](https://learnopencv.com/tag/yolov7/) - [yolov7 github](https://learnopencv.com/tag/yolov7-github/) - [yolov7 pose](https://learnopencv.com/tag/yolov7-pose/) - [yolov7 object detection](https://learnopencv.com/tag/yolov7-object-detection/) - [E-ELAN Architrcture](https://learnopencv.com/tag/e-elan-architrcture/) - [yolo architecture](https://learnopencv.com/tag/yolo-architecture/) - [yolov7 paper explanation](https://learnopencv.com/tag/yolov7-paper-explanation/) - [yolov7 detector](https://learnopencv.com/tag/yolov7-detector/) - [new yolo](https://learnopencv.com/tag/new-yolo/) - [confusion matrix](https://learnopencv.com/tag/confusion-matrix/) - [recall](https://learnopencv.com/tag/recall/) - [model evaluation metric](https://learnopencv.com/tag/model-evaluation-metric/) - [datasets](https://learnopencv.com/tag/datasets/) - [11 point interpolation](https://learnopencv.com/tag/11-point-interpolation/) - [coco map](https://learnopencv.com/tag/coco-map/) - [coco metric](https://learnopencv.com/tag/coco-metric/) - [average precision](https://learnopencv.com/tag/average-precision/) - [map iou](https://learnopencv.com/tag/map-iou/) - [Model accuracy](https://learnopencv.com/tag/model-accuracy/) - [pascal voc metric](https://learnopencv.com/tag/pascal-voc-metric/) - [mean average precision](https://learnopencv.com/tag/mean-average-precision/) - [Precision-Recall Curve](https://learnopencv.com/tag/precision-recall-curve/) - [precision](https://learnopencv.com/tag/precision/) - [evaluation metric](https://learnopencv.com/tag/evaluation-metric/) - [map metric](https://learnopencv.com/tag/map-metric/) - [map evaluation](https://learnopencv.com/tag/map-evaluation/) - [map object detection](https://learnopencv.com/tag/map-object-detection/) - [coco lvis](https://learnopencv.com/tag/coco-lvis/) - [YOLO3](https://learnopencv.com/tag/yolo3/) - [mean average precision example](https://learnopencv.com/tag/mean-average-precision-example/) - [iou computer vision](https://learnopencv.com/tag/iou-computer-vision/) - [iou meaning](https://learnopencv.com/tag/iou-meaning/) - [groundtruth meaning](https://learnopencv.com/tag/groundtruth-meaning/) - [how to calculate precision](https://learnopencv.com/tag/how-to-calculate-precision/) - [confusion matrix calculator](https://learnopencv.com/tag/confusion-matrix-calculator/) - [apple](https://learnopencv.com/tag/apple/) - [face tracking](https://learnopencv.com/tag/face-tracking/) - [fine tuning yolov7](https://learnopencv.com/tag/fine-tuning-yolov7/) - [custom training](https://learnopencv.com/tag/custom-training/) - [pothole detection](https://learnopencv.com/tag/pothole-detection/) - [training yolov4](https://learnopencv.com/tag/training-yolov4/) - [yolov4 custom training](https://learnopencv.com/tag/yolov4-custom-training/) - [document segmentation](https://learnopencv.com/tag/document-segmentation/) - [deeplabv3](https://learnopencv.com/tag/deeplabv3/) - [synthetic data](https://learnopencv.com/tag/synthetic-data/) - [custom training deeplabv3](https://learnopencv.com/tag/custom-training-deeplabv3/) - [Classical Computer Vision](https://learnopencv.com/tag/classical-computer-vision/) - [DSFD](https://learnopencv.com/tag/dsfd/) - [YuNet](https://learnopencv.com/tag/yunet/) - [Face Landmarks](https://learnopencv.com/tag/face-landmarks/) - [Detection Metrics](https://learnopencv.com/tag/detection-metrics/) - [SSD](https://learnopencv.com/tag/ssd/) - [Facial Detection](https://learnopencv.com/tag/facial-detection/) - [Face Applications](https://learnopencv.com/tag/face-applications/) - [face detection guide](https://learnopencv.com/tag/face-detection-guide/) - [face detection 2022](https://learnopencv.com/tag/face-detection-2022/) - [what is face detection](https://learnopencv.com/tag/what-is-face-detection/) - [face detection tutorial](https://learnopencv.com/tag/face-detection-tutorial/) - [evolution of face detection](https://learnopencv.com/tag/evolution-of-face-detection/) - [history of face detection](https://learnopencv.com/tag/history-of-face-detection/) - [face detection complete guide](https://learnopencv.com/tag/face-detection-complete-guide/) - [face detection history](https://learnopencv.com/tag/face-detection-history/) - [face detection evolution](https://learnopencv.com/tag/face-detection-evolution/) - [face detection algorithms](https://learnopencv.com/tag/face-detection-algorithms/) - [face detection methods](https://learnopencv.com/tag/face-detection-methods/) - [DLA-34](https://learnopencv.com/tag/dla-34/) - [re-ID](https://learnopencv.com/tag/re-id/) - [MOT](https://learnopencv.com/tag/mot/) - [FairMOT](https://learnopencv.com/tag/fairmot/) - [multiple object tracking](https://learnopencv.com/tag/multiple-object-tracking/) - [Kalman Filter](https://learnopencv.com/tag/kalman-filter/) - [Metaverse](https://learnopencv.com/tag/metaverse/) - [GeForce](https://learnopencv.com/tag/geforce/) - [driver alertness detection](https://learnopencv.com/tag/driver-alertness-detection/) - [driver fatigue alarm](https://learnopencv.com/tag/driver-fatigue-alarm/) - [drowsy driver alert system](https://learnopencv.com/tag/drowsy-driver-alert-system/) - [sleep detection sensor](https://learnopencv.com/tag/sleep-detection-sensor/) - [ford driver fatigue warning system](https://learnopencv.com/tag/ford-driver-fatigue-warning-system/) - [driver fatigue warning](https://learnopencv.com/tag/driver-fatigue-warning/) - [drowsy driver detection](https://learnopencv.com/tag/drowsy-driver-detection/) - [driver alert rest suggested](https://learnopencv.com/tag/driver-alert-rest-suggested/) - [driver fatigue system](https://learnopencv.com/tag/driver-fatigue-system/) - [driver drowsiness monitoring](https://learnopencv.com/tag/driver-drowsiness-monitoring/) - [driver warning rest suggested](https://learnopencv.com/tag/driver-warning-rest-suggested/) - [driver alert system](https://learnopencv.com/tag/driver-alert-system/) - [consider taking a break hyundai](https://learnopencv.com/tag/consider-taking-a-break-hyundai/)