Research On Vehicle License Plate Recognition System And Related Techniques

With the quick development of the society, car has became an important tool in people's life , more and more attention is being paid to the Intelligent Transportation Systems(ITS). Automatic Vehicle License Plate Recognition Systems(LPRS) is the main part of the contemporary ITS, and it has been more ad more important with great application fields in our life. Compared with traditional vehicles managing methods, it improves managing efficiency and level, and saves manpower and material resources, realizes scientific standard management and ensures traffic order. Therefore, it has comprehensive application prospect.The text introduced the design of LPRS, and it involve structure, functions, function index sign and environmental performance configure. The kernel technology of LPRS are: license plate locating, character segmentation and character recognition of Vehicle License Plates. The detection of license plates is the key of LPR system. Because of the complex of image background, the uncertainty of plate position and image quality, the location of plates is not satisfied. Therefore, the study on the algorithm of license plate location is always the hotspot and difficult problem. The dissertation analyzed and compared with algorithms of license plate locating and character segmentation related to LPRS deeply and presented my own viewpoints. First, a segmentation phase locates the license plate within the complicated image, so we made a research of vehicle license plate locating based on gray-scale, and presented a license plate location approach based on the vertical texture characteristics of characters; Second, had the license plate which inclined to use the method of edge detection and Hough changes phase change union effectively discriminated different type vehicles license plates, then calculated some parameters using the characteristic projection method, introduced the concept of character narrow region, carried on the character region classified processing, enhanced the division accuracy.This article used the car license pictures which photographed .under each kind of actual transportation environment for the above algorithm to carry on the experiment, The results of experiments show that the methods that we designed on the one hand enhanced car license processing accuracy, on the other hand reduced the car license process time in the certain degree, therefore even more suited applies to the actual LPRS.