#160 · Primary category: Computer Vision

Chinese_license_plate_detection_recognition

deep-learning plate-recognition pytorch yolov5

yolov5 license plate detection and recognition, supports 12 Chinese plate types and double-layer plates.

Project last updated:06/05/26

GitHub Stars

1.9K

Forks

298

Contributors

2

License

GPL-3.0

Why we included this project

Chinese plates come in more varieties than most systems expect: single and double-row formats, green new-energy plates, police, embassy, and the special Guangdong-Hong Kong-Macau plates. This project handles twelve of those types in one pipeline, combining a YOLOv5 detector with a CRNN-style recognizer to locate the plate and read the characters. The repo ships ready-to-run scripts for images, video, and ONNX inference, so you can test it immediately, and the companion tutorials walk through retraining both models on your own data. That makes it a practical baseline for parking management, toll gates, or traffic enforcement teams that need something working in Chinese rather than a generic ANPR setup.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category