The Application of Shot Classification Based on C4.5 Decision Tree in Video Retrieval

摘要：

In this paper, we classify shots in the level of type in connection with several types of shots. By comparing the differences of low-level features from these types of shots, we extract motion information, color, and pixel differences as features for our experiment. Through the training of C4.5 decision tree, a bridge is built to eliminate the gap from low-level features to high-level semantic, and a good performance of shot classification is achieved.

关键词： C4.5 decision tree video Retrieval shot classification

作者: Yao Zhen Hu Dan Qu Yong Liu J ing

作者单位: Chongqing Three Gorges University Electronic Engineering College Wanzhou, Chongqing, China Xingyi Normal University for Nationalities Audiovisual education center Xingyi, Gui Zhou, China Chongqing Three Gorges University Wanzhou, Chongqing, China Chongqing Three Gorges University Network Information Center Wanzhou, Chongqing China

会议类型: 国际会议

会议名称: 2011 6th Joint International Information Technology and Artificial Intelligence Conference(2011年第六届IEEE联合国际信息技术与人工智能会议 IEEE ITAIC 2011)

会议地点: 重庆

会议语种:英文

页码: 426-429

在线出版日期: 2011-08-20（万方平台首次上网日期，不代表论文的发表时间）