Research and Implementation of an Improved Radon Transform for License Plate Recognition

Abstract

With the application of Internet of things in the field of transportation, the requirement of traffic control and safety management is increasing, the intelligent transportation has become the main direction of traffic management. License plate recognition technology is the application of video image recognition technology, and it is an important part of intelligent transportation system. The movement of vehicle license extraction from complex background and identified, extracted by the license plate image preprocessing, feature extraction, license plate character recognition technology to identify the vehicle grade, color and other information. In the traffic flow detection, control and guidance, the airport, the port, residential vehicle management, do not stop electronic toll collection(ETC), running red light and other illegal vehicle monitoring and vehicle anti-theft, etc., has broad application prospects. In this paper, the template matching is used to deal with the license plate image, location of the license plate area, character segmentation and recognition, the tilt plate recognition rate of 90%, after using Radon transform correction, recognition rate of up to 95%, has a good effect.