A scalable and versatile ANPR package leveraging YOLO for detection and multiple OCR options to accurately recognize license plates.
Project description
PyPlateX
High-Performance Scalable ANPR Package: Ready-to-Use, Simple, and Efficient License Plate Recognition
Unlock top-tier accuracy and scalability with cutting-edge ANPR solution in 3 line of code. Designed for seamless integration and ease of use, it delivers robust performance and reliability for all your license plate recognition needs.
Simple ready to use ANPR
Note: The ANPR.detect function is asynchronous, so ensure you use the await keyword when calling it within an async function.
Install from pypi.org
pip install pyplatex
from pyplatex import ANPR
anpr = ANPR()
det = await anpr.detect('./demo/plate-1.jpg')
print(det)
or
from pyplatex import ANPR
import asyncio
async def main():
anpr = ANPR()
plates = await anpr.detect('./demo/plate-1.jpg')
print(plates)
# Run the async main function
asyncio.run(main())
the output would be like
{
'is_plate': True,
'is_plate_confidence': 0.78,
'plate_number': 'MUN389',
'plate_number_confidence': 1.0
}
Dev TODO:
- Release a Inital Version
- Add a plate detection model
- Read and detect Plates
- Format output
- Integrate Cv2filters
- Change Cofidence to a round number
- Add a ocr Model
- Release a Initial Version
- Add a option to accept image as Tensor / numpy array
- Add auto filters tag
This is a pre-release version; there might be some bugs. If you encounter any issues or performance-related problems, please report them here. If you'd like to contribute to this project, you can create a pull request here.
Warning: Use this pre-release with caution as it may still have unresolved issues.
Happy Coding 🚀 ...
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.