A data-mining based video shot classification method - 文章详情页

作者：

Shiwei, Zhao (Shiwei, Zhao.) | Li, Zhuo (Li, Zhuo.) | Zhu, Xiao (Zhu, Xiao.) | Lansun, Shen (Lansun, Shen.)

收录：

EI Scopus

摘要：

A　novel　classification　method　of　video　shot　genre　based　on　data-mining　has　been　proposed.　Shot　boundary　detection　and　key　frames　extraction　are　firstly　performed.　Then,　some　visual　features　such　as　color　and　motion　are　extracted　for　the　key　frame　and　shots.　Furthermore,　decision　tree　is　applied　to　discover　the　rules　between　these　features　and　shots　genres　from　numerous　training　data.　These　rules　are　finally　exploited　to　classify　the　new　video　shots.　Experimental　results　show　that,　compared　with　the　method　based　on　SVM　(Support　Vector　Machine),　the　proposed　method　can　achieve　higher　detection　accuracy　and　the　rules　obtained　are　easy　to　comprehend.　©2009　IEEE.

关键词：

Classification (of information) Data mining Decision trees Image segmentation Support vector machines Trees (mathematics)

作者机构：

[ 1 ] [Shiwei, Zhao]Signal and Information Processing Laboratory, Beijing University of Technology, Beijing, 10012, China
[ 2 ] [Li, Zhuo]Signal and Information Processing Laboratory, Beijing University of Technology, Beijing, 10012, China
[ 3 ] [Zhu, Xiao]Signal and Information Processing Laboratory, Beijing University of Technology, Beijing, 10012, China
[ 4 ] [Lansun, Shen]Signal and Information Processing Laboratory, Beijing University of Technology, Beijing, 10012, China

通讯作者信息：

电子邮件地址：

zhao_shiwei@emails.bjut.edu.cn

查看成果更多字段

成果类型
所属机构

所有年份指定年份从至