Research Of License Plate Location Algorithm In License Plate Recognition System

Along with the rapid development of China's economy, our country's automobile quantity increases rapidly. In 2009, China's automobile industry has reached an unprecedented height, and the output or sales are highest in the world, surpassing the United States, Japan and other countries. At the same time, The Government also speeds up the step in infrastructure's construction. For example, the highway, the multi-level crossing bridge, and the parking lot are getting more and more. But the corresponding vehicle management system actually has not followed the step, and still pauses in primarily stage with labor management. How to realize the automatic traffic management, enhance the intelligent vehicle traffic safety, reduce traffic jams, improve transportation efficiency, reduce the pollution of the environment, and improve the efficiency in the use of highways are becoming more and more important. A variety of intelligent transportation systems have been produced. As a means of collecting information in intelligent traffic system, License Plate Recognition System has developed very rapidly in recently years. License plate recognition technology applied to various occasions. For example, The monitoring traffic,Urban traffic intersection of "electronic police",Highway access control,Electronic toll,Mobile inspection, speeding detection, etc.License plate identification technology mainly includes three parts, such as the license plate location technology, the character segmentation technology and the character recognition technology. The task is to determine the specific location in image license. License plate location is the first step. It is directly related to the effect of the whole system's final recognition. and It also affect the recognition rate of system. At the same time, it is a classic problems.In this thesis, a variety of conventional license plate recognition technology is investigated. Firstly image preprocessing technology is introduced; Secondly, based on the characteristics of the Chinese license plate, the existing algorithm of the license plate location algorithm is studied. By reviewing the existing classical car license localization methods, existing license plate location methods are divided into two categories:one is based on the gray image of vehicle license plate location, and the other is based on the color image of vehicle license plate location. In this thesis, a new algorithm based on license plate texture and HSV color is proposed, which can satisfy the system real-time request, and has the high robustness. Experiments show that compared with the existing algorithms, the new algorithm has obvious superiority in terms of speed, algorithm complexity, and precision.