Research Of The Vehicle License Plate Recognition System

With the development of the economy, the number of vehicles is rapidly increasing and the problem of transportation is more and more serious. Intelligent transport system (ITS) has become the central aspect of the development of traffic field. Vehicle License Plate Recognition(VLPR)System is the focus of ITS, and is regarded as one of the important research areas of traffic fields. As a special computer vision system, a VLPR System can capture a vehicle image automatically and identify the vehicle license plate(VLP) in the image. VLPR system involves the techniques of digital image Processing, computer vision, pattern recognition and artificial intelligence.Its key techniques include vehicle license plate location, character segmentation and character recognition. VLP location, which is to locate the Vehicle License Plate from a vehicle image, is the basis of VLPR systems. VL character segmentation is to segment the license image into single characters for recognition. Chinese characters and digits in thelicense plate are perceived in the character recognition process that is the kernel part of VLPR systems.This thesis is mainly about the following three parts:1.Vehicle license Plate automatic location:We perform color clustering in HSI color space using the color distance. Then, mathematical morphology operations are applied to cluster images to eliminate noise and disturbances.2.License plate image Processing and character image segmentation: We preprocess the image of the vehicle license. (including filtering based on math morphology, skew correction, and thresholding). At last, we segment the characters using two-dimension histogram and prior knowledge of the ratio of the width to the height of a Vehicle-License-Character. 3.License Plate Characters recognition:We recognize the characters based on the features picked out by a BP neural network...