计算机工程与应用
計算機工程與應用
계산궤공정여응용
COMPUTER ENGINEERING AND APPLICATIONS
2013年
8期
169-173
,共5页
车牌定位%边缘检测%字符分割%连通域%垂直投影%字符识别%支持向量机(SVM)
車牌定位%邊緣檢測%字符分割%連通域%垂直投影%字符識彆%支持嚮量機(SVM)
차패정위%변연검측%자부분할%련통역%수직투영%자부식별%지지향량궤(SVM)
license plate location%edge detection%character segmentation%connected domains%vertical projection%character rec-ognition%Support Vector Machine(SVM)
随着智能交通的不断发展,车牌识别系统已经成为其中的重要组成部分.车牌识别分为车牌定位、字符分割以及字符识别三个部分.提出了一种新型车牌识别方法.在车牌定位方面,采用双边缘检测车牌定位方法;对于字符分割则提出了寻找连通域与传统投影分割相结合的方法;在字符识别上,将分类器分为三组,同时对于易混淆的字符进行了再次分类,这种做法缩短了训练时间,提高了准确率.实验结果表明,所提出的方法具有识别率高和速度快等特点.
隨著智能交通的不斷髮展,車牌識彆繫統已經成為其中的重要組成部分.車牌識彆分為車牌定位、字符分割以及字符識彆三箇部分.提齣瞭一種新型車牌識彆方法.在車牌定位方麵,採用雙邊緣檢測車牌定位方法;對于字符分割則提齣瞭尋找連通域與傳統投影分割相結閤的方法;在字符識彆上,將分類器分為三組,同時對于易混淆的字符進行瞭再次分類,這種做法縮短瞭訓練時間,提高瞭準確率.實驗結果錶明,所提齣的方法具有識彆率高和速度快等特點.
수착지능교통적불단발전,차패식별계통이경성위기중적중요조성부분.차패식별분위차패정위、자부분할이급자부식별삼개부분.제출료일충신형차패식별방법.재차패정위방면,채용쌍변연검측차패정위방법;대우자부분할칙제출료심조련통역여전통투영분할상결합적방법;재자부식별상,장분류기분위삼조,동시대우역혼효적자부진행료재차분류,저충주법축단료훈련시간,제고료준학솔.실험결과표명,소제출적방법구유식별솔고화속도쾌등특점.
With the development of intelligent transportation, license plate recognition system has become an important part of it. License plate recognition can be divided into three procedures, including license plate location, character segmentation and character recognition. In order to achieve accurate license plate recognition, a novel approach is proposed in this paper. During the task of locating license plate, the double-edge detection method is adopted for positioning the license plate. And the combina-tion of finding connected domains and traditional segmentation of projection is applied for character segmentation. Regarding character recognition, three kinds of classifiers are utilized for improving classification accuracy and the strategy of reclassifica-tion of confusing characters is employed, which can shorten the training time and get higher accuracy. Experimental results dem-onstrate that proposed approach is able to achieve high recognition rate with reasonable computational complexity.
