Automatic detection and recognition of vehicle number plates using advanced machine learning techniques.
This is a full-stack application for automatic number plate detection and recognition. It leverages YOLOv5 for detecting number plates and PaddleOCR for recognizing characters from detected plates. Built with a Python-based backend and a React frontend for a user-friendly experience.
project-root/
βββ backend/
β βββ model/
β β βββ best.pt
β βββ main.py
β βββ requirements.txt
βββ frontend/
βββ node_modules/
βββ src/
β βββ components/
β βββ Dashboard.tsx
β βββ DetectionPanel.tsx
β βββ HistoryPanel.tsx
β βββ NotificationsPanel.tsx
β βββ NumberPlateDetection.tsx
β βββ StatsPanel.tsx
βββ styles/
βββ App.tsx
βββ index.css
βββ main.tsx
βββ vite-env.d.ts
You can download the pre-trained YOLOv5 model weights from the following link:
β‘οΈ Download Model Weights
Place the downloaded weights (best.pt
) into the backend/model/
directory.
git clone https://github.com/alok-ahirrao/Number-Plate-Detection-System.git
Navigate to the backend directory, install dependencies, and start the server:
cd backend
pip install -r requirements.txt
python main.py
Backend API runs at: http://localhost:8000
Navigate to the frontend directory, install dependencies, and start the development server:
cd frontend
npm install
npm run dev
Frontend app runs at: http://localhost:5173
- FastAPI
- PyTorch
- YOLOv5
- PaddleOCR
- OpenCV
- React
- Vite
Feel free to improve this project by submitting pull requests. Your contributions are welcome!
Copyright Β© 2025, Alok Ahirrao
Licensed under the Creative Commons Attribution-NonCommercial 4.0 International License. You may use or modify this project for personal or educational purposes only. Commercial usage requires explicit permission.
For inquiries, please contact [email protected].
π Happy Coding! π