首页 | 本学科首页   官方微博 | 高级检索  
     

基于连通域分析和支持向量机的传真图像关键词定位
引用本文:蔡锋,刘立柱.基于连通域分析和支持向量机的传真图像关键词定位[J].计算机应用,2010,30(5):1259-1261.
作者姓名:蔡锋  刘立柱
作者单位:1. 信息工程大学信息工程学院2. 解放军信息工程学院
摘    要:电话号码区域定位是传真图像电话号码识别中的关键技术之一。首先采用连通域分析对传真图像实现较为精确的版面分析,形成比较完整的单词连通域,提取单词连通域的水平穿越次数和空间分布特征,形成51维的特征向量。采用基于正态决策树的多分类支持向量机(SVM),来完成对传真图像电话号码区域关键词的定位。实验结果表明,算法能够快速有效地完成关键词的定位,具有较强的实用价值。

关 键 词:连通域分析  水平穿越次数  空间分布特征  支持向量机  关键词定位  
收稿时间:2009-10-30
修稿时间:2010-01-21

Key words location of the fax images based on connected component analysis and SVM
CAI Feng,LIU Li-zhu.Key words location of the fax images based on connected component analysis and SVM[J].journal of Computer Applications,2010,30(5):1259-1261.
Authors:CAI Feng  LIU Li-zhu
Affiliation:College of Information Engineering/a>;Information Engineering University/a>;Zhengzhou Henan 450002/a>;China
Abstract:Locating the telephone number region is a very important technology in telephone number recognition of the fax images.After realizing a relative precise page analysis on the fax images by adopting the Connected Component Analysis (CCA) to form comparatively whole word regions,the features of horizontal traversing times and spatial distribution were abstracted to form feature vector of fifty-one dimensions.The multi-class Support Vector Machine (SVM) based on normal decision tree was introduced to achieve th...
Keywords:Connected Component Analysis (CCA)  horizontal traversing times  spatial distribution feature  Support Vector Machine (SVM)  key words location  
本文献已被 CNKI 万方数据 等数据库收录!
点击此处可从《计算机应用》浏览原始摘要信息
点击此处可从《计算机应用》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