The Research On Vehicle License Plate Location And Segmentation In License Plate Recognition System

With the high-speed development of our national economy and the improvement of our social intelligence, the management of transportation shows a tendency to intelligentize. Vehicles'license plate recognition (LPR) system is the main part of the Intelligent Transportation System (ITS), and it can be applied to various vehicle management to improve managing efficiency and level, save manpower and material resources, realize scientific standard management and ensure traffic order. Therefore, it has comprehensive application prospect. The automatic detection of license plate is one of the key technologies in LPR system. Because a license image is taken outdoors, the image background is complicated, and there is serious disturbance in the image so that the image quality is bad. The location of plate is not good enough. Therefore, the study on the algorithm of license plate location is always the hotspot problem. The followings are the major tasks in the thesis: (1) We have collected large numbers of interrelated data, and then summarized the latest research achievements and development of license plate location and segmentation. (2) We analyzed the characteristic of license image, especially in license plate area, and then defined the density of peak as the most important parameter. (3) On the basis of the defined parameter, we adopted the adaptive genetic algorithm (AGA) to locate and segment the licenses. Experimental results show that this algorithm can locate the license but not sensitive to unconstrained illumination conditions and irregular background. (4) Considering the lean of vehicle license plate, we adopted Radon transform to detect the lean angle and made some compensation. (5) Finally, we located and segmented the vehicle license plate exactly. This paper presents methods for location and segmentation of licenses based on AGA, and adjustment of the lean vehicle license plate based on Radon transform in details. At the end of the paper, we introduce the prospect of the future work.