This project involves a system for detecting license plates in images and extracting text from them using YOLO models and OCR technology.
To install the required dependencies for this project, run:
pip install -r requirements.txtYou also need the pretrained weights found int the link
Download those two files to your computer and add them to ./weights/ folder.
weights folder should have 2 config files and 2 weights files by the end of this operation.
Run the main script to start the plate detection and OCR process. The system can be used to detect license plates from images and extract the text from them.
python plate.pyIf using python3 on Unix like systems.
python3 plate.py- Plate Detection: Detects license plates in an image using YOLO models.
- OCR: Extracts text from the detected license plate.
- Gradio Interface: Simple UI
- Edge cases for ww cars, latin cars
- Edge cases for empty images, skewed
- Our own locally trained model on UM6P dataset
- Vehicle detection and BB detection
- Support for video 15fps to 30fps
- Dockerize the project
Contributions to the project are welcome. Please ensure to follow the coding standards and submit pull requests for any new features or bug fixes.
This project is licensed under the MIT License. See the LICENSE file for more details.