Vehicle License Plate Recognition System

The highway toll system is a important cmponent of the highway manag ement system and In thelligent Transportation system.In this article, through the study to character recognition and vehicle style recognition in the highway toll system , the calculate way of preprocessing, images, classification of characteristics is designed and realizied. Being based on several methods of AVI this thesis designs a compound system using infrared and piezoelectricity sensor. It is original to use piezoelectricity sensor getting the vehicular information including the number of tyre and axle. Design to use a single line of infrared detector getting the high of the vehicle. This design predigests the system greatly.At the same time, we designs system of the the vehicle plate recognition to raise the precision of vehicle recognition Based on the characteristic that vehicle license plates have plentiful edge information, the method of fuzzy template matching is carried out to locate the vehicle license plate, which has high location ratio.the method of characters preprocessing is discussed in detail. The method of silhouette projection is used to segment characters.The method of linear interpolation is applied in order that the mosaic phenomenon brought out by size normalization should be overcome, moreover, two types of eharWer size are used because of Chinese characters'and letters'different stroke density. A high premium on their priority Is put considering the regular character arrangement in the vehicle license plate.Finally, the fusion model is put forward, which combines the recognition results of the vehicle style with those of the license plate systematically and enhances the precision and credibility of vehicle recognition.