%0 Journal Article %A CAI An-ni %A JIA Guo-li %A ZHAO Zhi-cheng %T Moving Caption Detection Using Context and Relevance Vector Discriminant Analysis %D 2013 %R 10.13190/jbupt.201303.6.zhaozhch %J Journal of Beijing University of Posts and Telecommunications %P 7-10,15 %V 36 %N 3 %X

A moving caption detection method based on relevance vector machine (RVM) and the context of moving caption is proposed. Harris corner detector is used to determine caption region of video keyframes, and then the sparse optical flow field is obtained from Horn-Schunck(HS) optical flow algorithm, meanwhile, the motion and static text features is extracted respectively as well. A spatial-temporal context relationship among multiple text frames is described by features cascading. Finally, the relevance vector is learned and a two-class classifier is constructed. Experiments show that the performance of the proposed method is better than the existing four approaches, and supports vector machine-based algorithm.

%U https://journal.bupt.edu.cn/EN/10.13190/jbupt.201303.6.zhaozhch