Research And Application Of The City Vehicle Checking System Based On License Plate Identification Technology

In recent years, with the development of the License Plate Identification Technology, the Identification Technology is becoming mature. At the same time, the correlated domanial study based on the License Plate Identification Technology is more and more. This paper is based on the technology using on Police City Checkpost System. The License Plate Identification is well used for the practice.The License Plate Identification Technology integrates Computer Vision Technology and Pattern Identification Technology. There are mainly four steps for the License Plate Identification Technology in this paper: image pretreatment, plate location, character segmentation and character recognition. Image Pretreatment: process images by using gray level transformation, smooth denoising and contrast swell, improve the quality of the image. That is basic of the Plate Identification. Plate Location: acquire accurately the plate area from the images; using the arithmetic based on texture character. Character Segmentation: segment the plate area which is acquired by the previous step, until each smaller area only include one character. Character Recognition: recognize every Chinese character, letter and figure in the area, with the help of plate character.In this paper, the plate recognition technology aims at dynamic vehicle, being the same with running vehicle. For this demand, plate location is the most important technique in this system. Several algorithms proposed traditionally are compared with that in this thesis. Several common points are summarized, and a new location algorithm is then put forward. The new method includes: coarse location, exact location and precision correcting. That ensures the correctness of plate location.All the methods do not depend on the plate position in the image, have robust for the incline, distortion and character's pollution of the plate, and can adapt the change of environal ray and image contrast. The result of the system test proves that the correct rates of the plate location and character recognition are more than 90 percent. After finishing the plate identification, this paper introduces the demands and functional frame of the system. Then, it is described that includes the holistic structure, the partition of detail modules, and the tools of Visual Basic and Oracle which used for the system. At the last part, the main interface of the system is shown.