Automatic vehicle license plate detection and recognition

Abstract

Automatic Number Plate Recognition (ANPR) is an important application of computer vision and deep learning that has numerous practical applications in areas such as traffic management, law enforcement, and parking management. This ANPR system is a technology that uses optical image recognition to read vehicle license plates. It uses the Open-Source Computer Vision (OpenCV) and Easy Optical Character Recognition (EasyOCR) libraries for this purpose. It can be used in existing closed-circuit television systems, traffic surveillance cameras, or specially designed cameras. After capturing the images from the cameras, the data undergoes preprocessing as the first step. The edges are then found using the Canny edge detection technique. The license plate is detected by analyzing the contours of specific areas. The license plate is recognized using Optical Character Recognition (OCR) technology. We have achieved high accuracy in both the detection and recognition models.