Research And Accomplish On Automatic Recognition Technique Of License Plate

The vehicle License Plate Recognition (LPR) system is expected to have numerous applications in many fields. In this paper the full system of the vehicle license plate recognition is discussed in detail. The full system can be divided into four parts: Picture capture, License plate locating, Character segmentation, Character recognition.Picture capture: A reasonable and usable scheme of image obtaining ispresented afteran analysis of image obtaining technique which will be used in the intelligent vehicle plate recognization system. The scheme is discussed in detail of the system of motion capture base on sigle chip computer control.This scheme can be used to obtain a perfectand clear vehicle plate image in complex environment.License plate locating: We use the method based on the idea of two dimenion color histogram. First, to reduce the redundancy color information we cluster the color of the whole vehicle image into several colors. Second, we get the two dimenion color histogram from the vehicle image. Third, we search the vehicle licence based on the geometric and color property of licence automatically from the vehicle image.Character segmentation: First, we pre-process the image of the vehicle license (including filtering based on math morphologic, skew correction, thresholding and normalize). Second, we get the two dimenion color histogram of the licence image and use a threshold to cut the licence character based on the two-dimension histogram.Character recognition: This part is the most important part of LPR.We recognizes the character based on the features picked out by K-L transfom and by Vector Quantization.