首页 | 官方网站   微博 | 高级检索  
     

基于笔画和Adaboost的两层视频文字定位算法
引用本文:程豪,黄磊,刘昌平,谭怒涛.基于笔画和Adaboost的两层视频文字定位算法[J].自动化学报,2008,34(10):1312-1318.
作者姓名:程豪  黄磊  刘昌平  谭怒涛
作者单位:1.汉王科技股份有限公司 北京 100193
基金项目:国家高技术研究发展计划(863计划)
摘    要:在定位和验证的两级框架下提出了一种新的视频文字定位算法. 在定位模块中, 充分利用字符的笔画属性, 引入对字符区域有很强的响应的笔画算子; 经笔画提取, 密度过滤, 区域分解得候选文本行. 在验证模块中, 提取对文字有较强鉴别能力的边缘方向直方图特征, 使用Adaboost算法训练的分类器对候选文本行进行筛选. 实验结果表明, 该算法具有较强的鲁棒性, 在不同类型的视频帧中都能得到较好的定位结果.

关 键 词:文字定位    笔画提取    边缘方向直方图    Adaboost    视频OCR
收稿时间:2007-10-12
修稿时间:2008-1-11

A Two-Level Video Text Localization Algorithm Based on Strokes and Adaboost
CHENG Hao,HUANG Lei,LIU Chang-Ping,TAN Nu-Tao.A Two-Level Video Text Localization Algorithm Based on Strokes and Adaboost[J].Acta Automatica Sinica,2008,34(10):1312-1318.
Authors:CHENG Hao  HUANG Lei  LIU Chang-Ping  TAN Nu-Tao
Affiliation:1.Hanwang Technology Co. Ltd., Beijing 100193;2.Character Recognition Engineering Center, Institute of Automation, Chinese Academy of Sciences, Beijing 100190
Abstract:This paper proposes a new video text localization algorithm in a localization-to-verification framework.In the localization module,to take full advantage of character stroke attribute,the algorithm introduces a stroke operator which has a strong response to text regions;subsequently,it performs strokes extraction,stroke density filtration and region decomposition to obtain candidate text boxes.In verification module,the algorithm extracts edge oriental histogram features,which have strong discriminabilities for text and non-text,then the Adaboost classifier is used to verify candidate text boxes.Experimental results demonstrate that the proposed algorithm has strong robustness and is capable of obtaining relatively good localization results in various types of video frames.
Keywords:Text localization  stroke extraction  edge oriental histogram  Adaboost  video OCR
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《自动化学报》浏览原始摘要信息
点击此处可从《自动化学报》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