文献类型：会议论文

英文题名：A robust caption detecting algorithm on MPEG compressed video

作者：Wang, Yaowei[1];Su, Limin[2];Ye, Qixiang[3]

第一作者：Wang, Yaowei

通讯作者：Wang, YW[1]

机构：[1]Beijing Inst Technol, Dept Elect Engn, Beijing 100080, Peoples R China;[2]Beijing Union Univ, Informat Sch, Beijing 100101, Peoples R China;[3]Chinese Acad Sci, Grad Sch, Beijing 100080, Peoples R China

第一机构：Beijing Inst Technol, Dept Elect Engn, Beijing 100080, Peoples R China

通讯机构：[1]corresponding author), Beijing Inst Technol, Dept Elect Engn, Beijing 100080, Peoples R China.

会议论文集：International Workshop on Multimedia Content Analysis and Mining

会议日期：JUN 30-JUL 01, 2007

会议地点：Weihai, PEOPLES R CHINA

语种：英文

外文关键词：Algorithms - Text processing

摘要：Captions (or overlay texts) play an important role in video content understanding. In this paper, an algorithm is proposed to detect captions in MPEG compressed video. First, energy features, which are used to find candidate caption blocks, are extracted from DCT coefficients. Second, temporal information is employed to verify these candidate blocks. Then, a new region growing method named "density-based region growing" is proposed to connect these blocks into candidate text regions. Finally, the regions are identified as caption or non-caption by structural information of caption regions. Experiments are conducted on news videos and it is shown that the algorithm is feasible and effective in finding captions.