Font Size: a A A

Study Of Algorithm On Vehicle License Plate Automatic Recognition

Posted on:2005-11-02Degree:MasterType:Thesis
Country:ChinaCandidate:C J MuFull Text:PDF
GTID:2168360122497762Subject:Computer application technology
Abstract/Summary:PDF Full Text Request
With the rapid development of the road transportation, the traditional management by hand cannot meet the practical demands nowadays. In these years, more and more attention is being paid to the application of telecommunication and computer technologies in transportation and it is developing fester and fester. Now our country road transportation is stepping in a information and digital era.As a special computer vision system, the Vehicle License Plate Recognition (VLPR) System can capture a vehicle automatically and identify the numbers in the image. It can be used in the road tolling system, access control system, stolen vehicle identification system and intelligent transportation system and so on, contributing a lot to the automation of the transportation management.In this paper, some new algorithms and methods are introduced in such stages as processing of images, classification of characteristics and character recognition. At the same time, discuss the key problems and put forward some new methods aiming at the status now in this field.VLP location. A kind of location method of VLP image based on texture feature is put forward in this paper. And put forward a quartic location method, it considers the variety of actual vehicle image, and takes different operations on different image, achieving the goal of drawing the VLP.Type judgement. This paper presents a method of determining the type of a VLP based on the gradient histogram and the gray histogram of the image of a VLP.Character segmentation. This paper presents a binarization method based on the combination of dynamic threshold method and static threshold method, on the basis of this, puts forward a VLP character segmentation method based on Chinese character. This method can draw the characters of a VLP, especially it's quality is poor.Character recognition. Extract many structure features of character, and use these features to classify thickly and then subdivide by template matching and feature analysis. This method can recognize characters effectively through combining serial discerning machine and side-by-side discerning machine.This study systemically investigates algrithms of Vehicle Licese Plate Recognitonm (VLPR), Some methods in Which will be helpful for the studying on VLPR System.
Keywords/Search Tags:Vehicle license plate recognition, Vehicle license plate locating, Character segmentation, Edge detection, Mathematical morphology
PDF Full Text Request
Related items