Journal of Beijing University of Posts and Telecommunications

  • EI核心期刊

JOURNAL OF BEIJING UNIVERSITY OF POSTS AND TELECOM ›› 2006, Vol. 29 ›› Issue (2): 123-126.doi: 10.13190/jbupt.200602.123.caojr

• Reports • Previous Articles     Next Articles

Semantic Extraction of Video Keyframe Using Support Vector Machines

CAO Jian-rong, CAI An-ni   

  1. School of Telecommunication Engineering, Beijing University of Posts and Telecommunications
  • Online:2006-04-28 Published:2006-04-28

Abstract: A multi-class support vector machine (SVM) is used to classify the video key frames of scenery documentary. The color histogram features and MPEG (Moring Picture Expert Group)-7 edge histogram features from the video key frames of scenery documentary are combined to classify the key frame in SVM in order to obtain the semantics of the key frames. The performances of SVMs with difference kernel functions have been tested and compared. The precision of classification of SVM with polynormal and radial basis function will be about 3% higher than that of other kernel function.

Key words: support vector machine, key frames, semantic, video