spmallick/learnopencv

LearnOpenCV is a code repository that pairs with the LearnOpenCV.com blog. It collects working code examples for hundreds of articles covering computer vision, deep learning, and AI. Computer vision is the field of teaching machines to understand and interpret images and video, things like detecting objects in a photo, tracking moving people in a video, or reading text from a scanned document. Each folder in the repository corresponds to a specific blog post, covering topics ranging from basic image processing with OpenCV (a widely used computer vision library) to cutting-edge techniques like object detection with YOLO models, image segmentation, 3D reconstruction, and running AI models on small edge devices like Arduino or Jetson boards. There are also examples for large language models, visual question answering, and retrieval-augmented generation (where an AI looks up relevant documents before answering). The code is written in Python and C++, with many examples provided as Jupyter Notebooks, interactive documents that mix explanatory text with runnable code, making it easy to follow along step by step. You'd use this if you're learning computer vision or AI, want to experiment with techniques discussed in the LearnOpenCV articles, or need a starting point for building your own vision-based application. It's intended as a practical learning companion rather than a standalone tool.