Author : Rashmita Pandey 1
Date of Publication :11th July 2023
Abstract: License plate detection and extraction are essential tasks in various applications, such as traffic monitoring, parking management, and law enforcement. In this research, we have explored the use of YOLOv3, YOLOv4, and YOLOv5 models for license plate detection and evaluated their performance. We found that the YOLOv5 model outperforms the other models in terms of accuracy and speed. For license plate number extraction, we have used the Easy OCR model, which provides state-of-the-art performance in recognizing license plate characters. The proposed system was trained on the Open Image dataset and tested on the dataset captured by us, achieving an overall mAP50 of 88% for license plate detection and 87% for Vehicle detection. Our results demonstrate the potential of using deep learning models for license plate detection and recognition, and we believe that our findings will be useful for future research in this field.
Reference :