Real-time License Plate Recognition
An intelligent platform designed to instantly recognize and extract text from Bangladeshi vehicle license plates. Whether it's a private car or a commercial truck, simply upload an image to get accurate, real-time vehicle registration details.
About the Research
This platform is the culmination of a comprehensive research project focusing on Bangladeshi Vehicle License Plate Detection and Character Recognition. Utilizing state-of-the-art computer vision, this system is engineered to solve real-world problems like automated toll collection, traffic law enforcement, smart parking systems, and security surveillance.
The model is trained extensively to detect and recognize both commercial and non-commercial vehicle license plates, specifically optimized for the Dhaka and Chattogram regions.
Phase 1: Localization
Detection of license plates in unconstrained real-world images using a highly optimized dataset of 1,355 raw images.
- YOLOv11n selected as the superior model
- High Precision: 98.43%
- Overall Accuracy (mAP50): 94.49%
Phase 2: OCR Extraction
Extracting complex strings using a 30-class recognition model trained on 36,768 character instances.
- Detects 30 distinct Bengali and numeric classes
- YOLOv11n selected for string extraction
- High Precision: 91.71%
- Overall Accuracy (mAP50): 93.40%