500 AI Machine learning Deep learning Computer vision NLP Projects with code
Image Processing and Deep Learning algorithm to detect leopards from a live camera feed.
Screen Recorder Project with OpenCV and C++ on Ubuntu
Using YOLOv8s and YOLOv5s network. Model optimization: based on YOLOv8s, the original detection Head is replaced by Dynamic Head, and the FasterNet lightweight module is introduced. Finished ablation experiments.
AI-powered Diabetic Retinopathy detection using ResNet-50, FastAPI, React, Docker and PyTorch. Full stack clinical screening system with Bayesian decision theory and TTA ensemble.
ADAS system for Indian road scenarios using YOLOv8-Seg for road segmentation, object detection, and instance segmentation, trained on diverse real-world datasets with superpixel refinement and real-time inference capabilities.
基于计算机视觉（姿态估计）的运动动作识别、规范性评估与实时反馈系统 核心对比：MediaPipe+1D-CNN+GRU vs 传统DTW模板匹配 / 规则驱动方法 应用场景：大众健身、居家体能训练、青少年体测辅导 (桌面端/移动端)
🧠 Explore deep learning through hands-on projects, implementing neural networks like CNNs, RNNs, and Transformers using Python and TensorFlow.
Desktop human pose estimation app for images, webcam, and video using MediaPipe, YOLO Pose, React, Tauri, Rust, and Python.
Apple Tree Diseases Predication using Image Classification
Sports Ball Detection using Python, OpenCV and classical image processing techniques.
Touchless music control via hand gestures — CNN + OpenCV, no keyboard needed. Real-time hand gesture recognition to play/pause and control volume, built with PyTorch & OpenCV.
skin disease classification using YOLOv8
YOLOv8 Nano + EigenCAM for interpretable road damage detection in intelligent transportation systems.
An AI-powered face recognition attendance system using Python, OpenCV, and Tkinter automate student attendance with real-time facial detection, image training, and CSV tracking.
Real-time autonomous driving perception system: detection, tracking, segmentation, and TensorRT C++ deployment
A computer vision pipeline exploring self-supervised learning (SSL) for label-efficient outdoor waste detection and multi-object tracking using YOLO and ByteTrack.
Real-time hand gesture recognition using a custom CNN and OpenCV to translate sign language gestures into text.
AI-powered face recognition attendance system using MediaPipe, FaceNet, OpenCV and Streamlit.
To associate your repository with the computer-vision-project topic, visit your repo's landing page and select "manage topics."