Research On The Vehicle License Plate Recognition

The Intelligent Transportation System (ITS) is the study topic in the front of the transportation realm of world currently. The Vehicle License Plate Recognition (VLPR), which is an important technique within the Intelligent Transportation System, combines the image processing, pattern recognition, automatization, etc. The use of the VLPR is becoming more and more widespread now.The vehicle license plate is the clearest, exactest, and exclusive symbol of vehicles. The VLPR system which is a special vision system, can record the dynamic data of running vehicles automatically, judge and extract the image data of vehicle license plate effectively, and also can recognize the character of vehicle license plate precisely.This paper proposes a whole completed VLPR system. In this paper some works have been done, including over viewing the popular technique of the VLPR, and introducing the every component of the VLPR system. It is also discussed in this paper an image binaryzation algorithm which is based on gray level image, and a coarse positioning algorithm of vehicle license plate based on searching for the connected domain. It extracts the features of the plate area according to the inherent characteristics of the vehicle license plate, and uses the BP neural network to make accurate positioning. This paper also purposes a license plate binaryzation algorithm based on a color model, and segments the characters of the plate combining the perpendicular projection and connected domain in order to avoid character adhesion or excessively segment. At last the character will be recognized by extracting the weighted combining features to match the character model.The VLPR system discussed in this paper puts forward the technique of the VLPR existed, increases the speed and accuracy of the recognition, extends the application range, and realizes the requirement of real-time ITS.Experiment shows that this VLPR system is efficient in the real-time recognition system while not be sensitive to the unconstrained illumination conditions and irregular background. The plate location process is accurate and rapid.