首页 | 官方网站   微博 | 高级检索  
     

基于PCA和边缘不变矩的车标识别新方法
引用本文:王枚,王国宏,高小林,王勇.基于PCA和边缘不变矩的车标识别新方法[J].计算机工程与应用,2008,44(4):224-226.
作者姓名:王枚  王国宏  高小林  王勇
作者单位:1. 海军航空工程学院,电子通信系,山东,烟台,264001;烟台职业学院,计算机与信息工程系,山东,烟台,264000
2. 海军航空工程学院,电子通信系,山东,烟台,264001
3. 烟台职业学院,计算机与信息工程系,山东,烟台,264000
基金项目:国家自然科学基金 , 教育部全国优秀博士学位论文作者专项基金
摘    要:车标识别技术是进行车辆类型识别的关键内容。在车牌定位准确的基础上,利用车头图像中车牌、车标位置关系定位到车标大致区域;接着对车标进行精确定位、归一化处理,并提出似真度函数对车标进行确认;然后利用边缘不变矩的最小距离进行车标识别。该方法不受原始车标图像大小、变形等影响,能够自适应地进行目标定位确认和识别,具有较强的鲁棒性。通过实测图像测试,结果表明该方法是有效和可行的。

关 键 词:似真度函数  边缘不变矩  车标配准  车标识别
文章编号:1002-8331(2008)04-0224-03
收稿时间:2007-05-31
修稿时间:2007-07-31

New method of vehicle-logo recognition base on PCA and Edge invariant moment
WANG Mei,WANG Guo-hong,GAO Xiao-lin,WANG Yong.New method of vehicle-logo recognition base on PCA and Edge invariant moment[J].Computer Engineering and Applications,2008,44(4):224-226.
Authors:WANG Mei  WANG Guo-hong  GAO Xiao-lin  WANG Yong
Affiliation:1.Departerment of Electronic and Communication,Naval Aeronautical Engineering Institute,Yantai,Shandong 264001,China2.Departerment of Computer and Information Engineering,Yantai Vocational College,Yantai,Shandong 264000,China
Abstract:This paper presents a method of vehicle-logo location and recognition based on PCA and edge invariant moment.First,the approximate range of the vehicle-logo region can be located depending on the topology structure between vehicle plate and vehicle-logo.Then the vehicle-logo precise location,registration and detection are executed in order.The plausibility function is represented to ensure the real vehicle-logo.At last the vehicle-logo recognition is achieved by edge invariant moment minimum distance.The approach can adapt to complete object location and recognition with high robust.The experimental result on actual vehicle images shows that the method is practical and effective.
Keywords:plausibility function  edge invariant moment  vehicle-logo registration  vehicle-logo recognition
本文献已被 CNKI 维普 万方数据 等数据库收录!
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-23

京公网安备 11010802026262号