Research And Implementation Of Vehicle License Plate Recognition System

With the rapid development of domestic economy,number of cars.buses.trucks and other vehicles increases a great deal.More and more funds are put into the construction of roads, highways, parks by our goverment, which are essential to keep the booming market.Roads become broader and parking area have more space for drivers.However, as a very important part of transportation system, management dose not follow the steps of hardware constructions. As in the old days, almost everything is in the charge of human beings. To utilize the convenience of modern transportation, a way should be found to make good use of the existing transportation constuctions. Intelligent Transportation System(lTS), such as Automatic Traffic Signal Controll System, Gloabal Position System(GPS), Navigation System , Intelligence Yaffle Monitor System , Intelligent Residential Area Management System , plays a increasingly important role in the management of transportation . Because license plate is efficient in identifing vehicles , License Plate Recognition(LPR)is foundamental in ITS , In recent years , as the technology of manufactory progress .electronic equipment get higher performance . More theory in Digital Image Processing and Pattern Recogniton is put into practice .With the help of these progress ,the management in modern transportation system get all the essential conditions to make another giant progress .In this paper , we analysis the status of present transportation system , discuss some details in the field of License Plate Recognition .After all we recommended a prototype of LPR and give a preliminary realization of the key moduls.In general ,the prototype includes two parts .They are Image Collection Module(ICM) and Image Processing Module (IPM ).ICM is mainly consisted of hardwares such as cameras, switches, video card and cables. It monitors the video signal and cuts frame pictures at appropriate time .IPM , which is the key part of the prototype ,is realised by software .To realise it in a simpler way, it is first coded in the environment of Matlab .Our work is focused on the Image Processing Module (IPM) ,where license locating and character recognition are realised .To locate the license plate ,we take the two-step strategy .In the first step ,the static background is extracted ,as a result ,a general car picture is got .In the second step ,the license plate is located accurately .In step one ,the backgroud picture is dynatically fixed.The substraction between car image and background image is redefined to make the proess more effectively. According to the features of license plate ,the characters in the plate are divided into two groups .Chinese charaters and none Chinese charaters . ANN is the key tool in both groups .Recognition for none Chinese character is realised and as shown in the experiment .transformation have stronger impact than the evenly distributed noisy.There are six chapters in this paper. The background of this paper will be introduced in Charpter One . In Chapter Two ,some details are given to illustrate the hardwarecomposition of the system .Chapter Three is focused on the location method of license plate , while Chapter Four is focused on the recognition .And Chapter Five give a evaluation of our system .disclose some weakness and paint out some general solutions .The last chapter æ¡Ÿhapter Six, is a summary of writer's work ,and gives a prediction , which is about of the fut re tendency of LPR .This paper will refer to the fields of Digital Image Processing ,Pattern Recognition and Artificial Intelligence ,etc .