OpenCV is a computer vision library for image processing, video work, and machine perception tasks.
Open Source: #computer-vision
Catalog projects marked with #computer-vision. Tags work as dedicated landing pages, so related tools are easier to find and connect.
This collection holds 13 projects with a combined 699,591 GitHub stars. Main languages: Python, C++, Jupyter Notebook.
Repositories
PaddleOCR is an OCR toolkit for text and document-structure recognition across PDFs, images, multilingual OCR, and LLM-ready parsing.
Tesseract OCR is an engine for recognizing text in images and scans, with support for many languages and OCR scenarios.
Ultralytics is a Python package and CLI for YOLO models and computer-vision tasks.
YOLOv5 is Ultralytics’ popular PyTorch project for object detection and model export.
face_recognition is a Python library and command-line tool for face recognition, built on top of dlib.
Segment Anything is a Meta AI repository with the SAM model, inference code, examples, and checkpoint links.
Supervision is Roboflow’s Python library of reusable computer-vision tools.
PyTorch Image Models is a large collection of computer vision models for PyTorch.
Real-ESRGAN is a project for real-world image and video restoration and upscaling.
MediaPipe is Google’s set of ML solutions for live and streaming media.