首页 | 本学科首页   官方微博 | 高级检索  
     

基于矩和小波变换的数字、字母字符识别研究
引用本文:沈会良,李志能.基于矩和小波变换的数字、字母字符识别研究[J].中国图象图形学报,2000,5(3):249-252.
作者姓名:沈会良  李志能
作者单位:浙江大学信息与电子工程学系!杭州310027
摘    要:欲实现汽车监控和管理智能化,必须正确识别牌照字符,在识别过程中,关键是特征向量的提取,小波变换能有效地提取字符的结构特征,而矩能够很好的地其进行描述,该文提出了一种用线性矩和小波变换提取数字、字母字符特征的方法,实验证明该方法有很高的识别率,达到97%以上,能够有效地进行字符的分类,可满足实际应用。

关 键 词:字符识别  小波变换  汽车监控  信号处理  字符图象
收稿时间:1999/5/10 0:00:00
修稿时间:1999-05-10

A Study of Number and Letter Character Recognition Based on Moments and Wavelet Transform
SHEN Hui-liang and LI Zhi-neng.A Study of Number and Letter Character Recognition Based on Moments and Wavelet Transform[J].Journal of Image and Graphics,2000,5(3):249-252.
Authors:SHEN Hui-liang and LI Zhi-neng
Affiliation:Department of Information and Electronic Engineering,Zhejiang University,Hangzhou 310027;Department of Information and Electronic Engineering,Zhejiang University,Hangzhou 310027
Abstract:For the sake of vehicle identification and intelligent management, it's necessary to recognize the characters on the license in high accuracy. Selection of a feature extraction method is probably the most important factor in recognition process. The feature of number and letter character construction can be extracted by wavelet transform effectively and described by moments. A method of character recognition based on linearity moments and wavelet transform is presented in this paper. The result of experiment shows high recognition rate above 97%, which indicates that the method can be put into practical use.
Keywords:Character recognition  Feature vector  Moments  Wavelet transform
本文献已被 CNKI 维普 等数据库收录!
点击此处可从《中国图象图形学报》浏览原始摘要信息
点击此处可从《中国图象图形学报》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