Research Of License Plate Automatic Location In Intelligent Transportation System

The thesis is a part of the study on the LARS (License plate Automatic Recognition System). LARS is the important application of computer vision and pattern recognition in the intelligent transportation system. Finding the accurate location of the license plate is the key of the recognition of the license plate, and can improve the systematic discerning rate.It is a generally acknowledged problem relatively difficult to locate the license plate. The paper have collected and summarized a lot of materials about locating the license plate. After these, we propose a kind of license plate orient algorithm on the basis of the shape and lamination of the license plate. This algorithm is regarded the license plate area as a whole but not several characters while locating the license plate. The whole process of location can be divided into three stages: pretreatment of original image, search for the area of license plate and locate license plate.In the process of pretreatment of original image, firstly, the system eliminates the noise to improve the quality of image, and detects the edge of the image. And then, it joints all the upright edge in the image by the mathematical morphology operation in order to form many joint-areas. Through the course of searching for these joint-areas, we often get several compatible areas. Finally, we find the accurate location of license plate in the compatible areas according to some intrinsic characteristics of license plate.At the end of the paper, we realize the whole location system on the computer. The experimental result shows that this system can fastly, accurately find the location of license plate.