Updated the `README.md` to include:
- Comprehensive project overview.
- Detailed setup and usage instructions.
- Information on system architecture.
- Guidance for real-time recognition, static image testing, and CRNN training.
- License information.
This update ensures clarity for users and contributors, improving the overall documentation quality.
- Added `static-test.ipynb`, a Jupyter Notebook for testing the license plate recognition system on static images. The notebook demonstrates:
- Loading and preprocessing of test images.
- Inference using the YOLO and CRNN models.
- Visualization of detection results.
- Added the `img` folder containing test images of vehicles with license plates for validation and demonstration purposes.
These additions provide a comprehensive framework for testing and showcasing the system's capabilities on pre-captured images.
Added a Jupyter Notebook `train_crnn.ipynb` to the repository for training the CRNN model. This notebook includes:
- Steps for preparing the dataset.
- Training pipeline for the CRNN architecture.
- Evaluation of the trained model.
This addition enhances the project's flexibility for users who want to retrain the CRNN model on custom datasets.
itqop