%0 Journal Article
%T A Learning Based Approach to Validate Text in Video<br>一种基于学习的视频字幕验证方法
%A WANG Yong
%A LI Jian-bin
%A HU De-wen
%A ZHENG Hui
%A <br>王勇
%A 李建彬
%A 胡德文
%A 郑辉
%J 中国图象图形学报
%D 2006
%I 
%X For improving accuracy,validating text is a key step of detecting text in video.The current approaches mostly based on experiential rules.The approaches are not adaptive,in condition of complex background,low resolution,varied font,size,color of text in video.For improving adaptability and accuracy of validating text,the application of two-dimension principal component analysis(2DPCA) for video frame processing is investigated and a novel 2DPCA and support vector machine(SVM) based approach for validating text in video is proposed.The approach has two steps of training and validating.Firstly,2DPCA is adopted to get the features of video image patches.Then,SVM is trained to validate and classify video image patches.The experimental results illustrate that the novel approach for validating text in video is more effective and costs less time than the other approaches,in condition of complex background,low resolution,varied font,size,color of text in video.
%K text in video
%K text validation
%K 2DPCA
%K support vector machine(SVM)<br>视频字幕
%K 字幕验证
%K 2维主成分分析
%K 支撑向量机
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=D06194629680C940ACE75262F54B9D85&aid=6927CEE90AC8650A&yid=37904DC365DD7266&vid=708DD6B15D2464E8&iid=708DD6B15D2464E8&sid=E521CC33DC22B84E&eid=4BFBB19F1A63A4F0&journal_id=1006-8961&journal_name=中国图象图形学报&referenced_num=1&reference_num=14