The Persian License Plate Recognition (PLPR) system is a state-of-the-art solution designed for detecting and recognizing Persian license plates in images and video streams. Leveraging advanced deep learning models and a user-friendly interface, it ensures reliable performance across different scenarios.
This system aims to tackle the unique challenges associated with Persian license plate detection and recognition, offering high accuracy and efficiency. It's well-suited for applications in traffic monitoring, automated vehicle identification, and similar fields.
- Advanced Detection: Utilizes YOLOv5 models for high-accuracy license plate detection.
- Persian Character Recognition: Custom-trained models ensure precise recognition of Persian characters.
- Real-Time Processing: Capable of processing live video feeds in real-time.
- User-Friendly GUI: Intuitive graphical user interface simplifies interactions with the system.
- The main view to show the input (video/camera)
- Rectangle around the detected plate
- Image of the detected plate
- The text extracted from plate image
- Name of the owner of the plate
- Status of the plate which is (Allowed,Not Allowed, Non Registered)
- The table of last 10 enteries which we can add a non registered plate or see the information of the owner
- Python 3.8+
- Pip for Python package management
- Clone the repository and navigate to its directory:
git clone https://github.com/mtkarimi/smart-resident-guard.git cd smart-resident-guard - Install the required Python packages:
pip install -r requirements.txt
Launch the application with the following command:
python home-yolo.pyThe system's GUI enables users to upload and process images or video streams, displaying detected license plates and recognized text. It also allows for parameter adjustments to optimize performance.
For a deep dive into the PLPR system's architecture, model training, and advanced usage, check out our Wiki. It's a comprehensive resource for users and developers alike.
Explore the pdf-research directory for research papers and articles on LPR technologies, offering insights into the techniques and algorithms behind the system.
Heartfelt thanks to the open-source projects and communities that have made this project possible. Special mentions include:
- YOLOv5 and PyTorch for the core detection and recognition models.
- PySide6 and OpenCV for the application interface and image processing capabilities.
- Pillow for enhanced image manipulation.
This project stands on the shoulders of giants within the AI and open-source communities. Their dedication to sharing knowledge and tools has been invaluable.
GPL-3.0. See the LICENSE file for details.
I also want to thank the following individuals for their direct contributions, advice, or resources that have been instrumental in the success of this project:
