The Research On Vehicle License Plate Location And Segmentation Under Complex Backgroud

With the high-speed development of our national economy and the improvement of our social information, 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 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) A license plate locating approach based on color and texture characteristics is proposed, which fully exploit color information and other features of vehicle plate. Firstly license plate's RGB model is transformed to HSV model, then license plate is located through the color segment and area growth. Gradient detection based on projection is used to adjust the distorted license plate to horizontal position.(3) Image denoising and edge detection are finished by using wavelet transform.(4) A algorithm based on projection methods and template matching to segment characters is proposed.