首页 | 本学科首页   官方微博 | 高级检索  
     

基于投影信号和小波分析的字符特征提取方法
引用本文:赵莉,杨莉,林晓.基于投影信号和小波分析的字符特征提取方法[J].山东建筑大学学报,2007,22(3):247-250.
作者姓名:赵莉  杨莉  林晓
作者单位:1. 山东建筑大学,商学院,山东,济南,250101
2. 山东建筑大学,管理工程学院,山东,济南,250101
3. 山东建筑大学,资产处,山东,济南,250101
摘    要:设计了一种将传统的投影特征和小波多分辨分析相结合的字符特征提取方法,将直观易得但细分能力较差的字符投影信号,进行不同尺度下的小波多分辨分解,分别在获得的近似成份和细节成份中提取有效的特征量。并通过详实的对照试验分析说明了小波分解尺度和多尺度小波系数对字符特征描述的有效性影响。

关 键 词:小波分析  多尺度分解  投影特征  特征提取
文章编号:1673-7644(2007)03-0247-04
收稿时间:2006-10-12
修稿时间:2006-10-12

The character characteristic extraction based on projection characterist and wavelet analysis
ZHAO Li,YANG Li,LIN Xiao.The character characteristic extraction based on projection characterist and wavelet analysis[J].Journal of Shandong Institute of Architecture and Engineering,2007,22(3):247-250.
Authors:ZHAO Li  YANG Li  LIN Xiao
Affiliation:1. School of Business, Shandong Jianzhu University, Jinan 250101, China; 2. School of Management Engineering, Shandong Jianzhu University, Jinan 250101, China; 3. Asset Managing Department, Shandong Jianzhu University, Jinan 250101, China
Abstract:This paper presents a new method which combines the traditional projection characteristic and wavelet multiresolution analysis. The simple and crude character projection characteristic was transformed with wavelet multiresolution analysis, extracting the valid characteristic in the coefficients of approximation and particular. The result of control experiment illustrates the effect of wavelet multi-scale transform and wavelet coefficients on character characteristic extraction.
Keywords:wavelet analysis  multi-scale transform  projection characteristic  characteristic extraction
本文献已被 维普 万方数据 等数据库收录!
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