The Application Of Images Processing In Licenese Plate Recognition

With the high-speed development of our national economy,the owning amount of automobile has increased sharp,there are more and more construct in the domestic expressway,urban road and parking area,etc.The requisition of on the traffic control,safety management improves day by day.The Intelligent Transportation Systems has already become the main direction of present traffic administration development.Automatic License Plate Recognition(ALPR)is an important component of Intelligent Transportation Systems,and can be applied in many fields.The system can automatically register,verify,monitor vehicle or report to the police with automatic recognition for vehicle license plates.So it can be used in many kinds of occasions,such as the charges system of expressway,monitoring system at road and roll-gate,charge and monitoring system at the district,parking area,guide system, the system counting the quantity of vehicle passing in a certain period time,etc.Generally,ALPR system mainly comprises modules of image acquisition and preprocessing,plate location,character isolation and character recognition.As a result of experiment and time limit,The main designs of this article are as follows.image acquisition and preprocessing,plate location,character isolation.The article brings forward some effective strategies and completes some experiments basing on these three modules.(1)Image acquisition and preprocessing:In the image acquisition and preprocessing part,This article introduces the method of crossroad image acquisition.Then I contrast diversified image acquisition methods.Image preprocessing part include:Image's gradation cineration,cineration stretched,median filter,level adjustment.(2)Plate location and isolation:Plate location and isolation is a sticking point in my work,Its result has an important impact on the accuracy of the character recognition.This paper summarizes an algorithm integrating edge detection and iterative thresholding,based on extensive analyses and comparison of the existing algorithms.Then the algorithm is used to binarize the image.Furthermore,on the base of improvement towards the traditional projection,the location and segmentation of vehicle license plate is realized.The experimental results indicate that the experimental algorithm in this paper is more effective and more precise.It has the advantage that this algorithm remains the edge of the license plate and makes license plate different from the background as possible as it can.There is a more evident result when it is used to process the image of static vehicles.So it is fit for being applied to the locations such as car-parks and toll-stations.(3)Character isolation:On the premise of the accuracy of license plate location and isolation,This article puts forward a perpendicularity segmentation method which uses perpendicularity projection information and priori knowledge restriction.As the test result,it proves that this recognition method can relatively division characters and system's performance is good.The time of plate location and character isolation is less than 80ms,The success probability is higher than 90 percents.The entire system is algorithm simplicity and low degree complexity,It is able to satisfy the request that the fleetness character isolation.,It will bring reality value into play in fields such as intelligence traffic,study of image information.