| 21century is a century of intelligentialization, informatization, calculation and network, in this century with the character of digital calculation, as the basic technology of artificial intelligence technology, pattern recognition technology will certainly gain gigantic space for development. Recognition system of vehicle mainly consists of two key technologies: recognition of vehicle license plate (VLP) and recognition of vehicle type. It not only finds wide application in ITS, but also is a hot point of research in computer vision, image processing and pattern recognition. So its related technology is attended prevalently. On the above background, we made a deep and systematic research for recognition of vehicle. In recognition of VLP, the problems of VLP classification and character segmentation are studied in this dissertation. In recognition of vehicle type, differing with other researchers who attend to the recognition of shape, size of vehicle, we pay attention to the accurate location of the effective vehicle logo area.This paper presents a method to classify the different kinds of vehicle license plates. Our method use decision trees C4.5 algorithm and HSV space color information, use the intervals between the plate characters and the colors of the plates to classify different plates and to segment the characters of the plates based on color feedback, obtain the goal that we can classify the different plates and get a better segmentation between the characters, so it is an important part of the vehicle license plate segmentation and an assistance of the character recognition. Based on the foundation of vehicle plate recognition, this paper give the solve method of logo recognition, first we get the approximate position of the logo, and then we get rid of the noise of the exhaust panel and vehicle light, minimize the recognize area of the logo, increase the ratio of logo recognition. We give the results of the experiment to certify the effectiveness of this method. |
PDF Full Text Request