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. It means you can:
- Share Source Code: If you distribute binaries or modified versions, you must make the source code available under GPL-3.
- License: Must keep and apply GPL-3 to the modified work.
- State Modifications: If modified, must disclose that it was changed.
The Persian License Plate Recognition (PLPR) system is a testament to the collaborative spirit of the open-source community. While the assembly and development of this system were carried out independently, the project is enriched through the insights and resources offered by various exceptional contributors and datasets within the community. This section is dedicated to acknowledging those invaluable learnings and resources.
🫂 Learning from Community Leaders:
- Immense gratitude is directed towards Mahdi Rahmani and Meftun AKARSU. Although not directly involved in this project, their repositories served as significant learning resources. The knowledge gleaned from their work helped in navigating the complexities of license plate recognition and contributed to the foundation upon which PLPR was built.
🧱 Acknowledging Vital Datasets:
-
The datasets that played a pivotal role in the development of the PLPR system deserve special mention. I am deeply thankful for access to:
These resources were crucial for training and refining the recognition capabilities of the system. My heartfelt thanks go out to the creators and contributors of these datasets for their openness and dedication to advancing the field.
Open for Dialogue:
- Acting in the spirit of the open-source community means valuing transparency and open communication. Should there be any questions about how I utilized these contributions, or if there are specific concerns to be addressed, I am more than willing to engage in discussions. This project is a reflection of what can be accomplished through shared knowledge and cooperation, and I am committed to learning from and contributing back to the community.
I extend my sincerest appreciation to everyone whose work has indirectly contributed to the Persian License Plate Recognition system. Your tireless efforts and willingness to share knowledge have not only made this project possible but also continue to inspire and propel the open-source movement forward.
🌟 A Heartfelt Note:
- 🍁 Continuing Forward: This repository has reached a milestone and I've decided to not update it going forward. It stands as a testament to what we've achieved together.
- 📚 Inspiration and Acknowledgment: Much of what you've read and discovered here, including the detailed Wiki, was crafted with the assistance of ChatGPT. This AI has been an invaluable tool in articulating ideas and descriptions.
- 🌈 Gratitude and Learning: I encourage you to explore the works of the contributors and datasets mentioned here. Their efforts not only enriched this project but also provide vast oceans of knowledge and inspiration for us all.
- 🧩 The Journey: If there's one thing I've learned, it's that creativity is about connecting ideas. My role was more of an assembler, piecing together the incredible innovations and knowledge shared by the community to create something meaningful.
💖 Thank you all for your support, curiosity, and for joining me on this journey. Here's to the endless potential of collaboration and open source! 🥂