首页 | 本学科首页   官方微博 | 高级检索  
     

基于双边缘检测的车牌识别算法
引用本文:王 磊,王瀚漓,何良华. 基于双边缘检测的车牌识别算法[J]. 计算机工程与应用, 2013, 49(8): 169-173
作者姓名:王 磊  王瀚漓  何良华
作者单位:1.同济大学 计算机科学与技术系,上海 201804 2.同济大学 嵌入式系统与服务计算教育部重点实验室,上海 200092
摘    要: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。

关 键 词: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)  

License plate recognition based on double-edge detection
WANG Lei,WANG Hanli,HE Lianghua. License plate recognition based on double-edge detection[J]. Computer Engineering and Applications, 2013, 49(8): 169-173
Authors:WANG Lei  WANG Hanli  HE Lianghua
Affiliation:1.Department of Computer Science and Technology, Tongji University, Shanghai 201804, China2.Key Lab of Embedded System and Service Computing, Tongji University, Shanghai 200092, China
Abstract: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 combination 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 reclassification of confusing characters is employed, which can shorten the training time and get higher accuracy. Experimental results demonstrate that proposed approach is able to achieve high recognition rate with reasonable computational complexity.
Keywords:license plate location  edge detection  character segmentation  connected domains  vertical projection  character recognition  Support Vector Machine(SVM)  
点击此处可从《计算机工程与应用》浏览原始摘要信息
点击此处可从《计算机工程与应用》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号