Automatic Number Plate Recognition System using YOLO and PaddleOCR

This repository contains an Automatic Number Plate Recognition (ANPR) system implemented in Python using YOLO (You Only Look Once) for object detection and PaddleOCR for text recognition. The system is capable of detecting and recognizing license plates from images or video streams.

Requirements

Make sure you have the following dependencies installed:

• Python (>= 3.6)
• OpenCV (>= 4.0)
• numpy (>= 1.18)
• paddlepaddle (>= 2.1.0)
• paddleocr (>= 2.3.0)
• torch (>= 1.9.0)
• torchvision (>= 0.10.0)
• tqdm (>= 4.62.3)

Installation

1. Clone this repository to your local machine:

   git clone https://github.com/your-username/automatic-number-plate-recognition.git
   

2. Change into the project directory:

   cd automatic-number-plate-recognition
   

3. Install the required dependencies using pip:

   pip install -r requirements.txt
   

Usage

To run the script, follow these steps:

1. Go to /scripts
2. Run main.py

License

This project is licensed under the MIT License.

Acknowledgements

This ANPR system was built using the following libraries:

1. YOLO by Joseph Redmon,
2. PaddleOCR by PaddlePaddle.

Special thanks to the authors and contributors of these libraries for their valuable work