Classification of TV programs based on audio information using hidden Markov model

被引：52

作者：

Liu, Z ^{[1
]}

Huang, JC ^{[1
]}

Wang, Y ^{[1
]}

机构：

[1] Polytech Univ, Dept Elect Engn, Brooklyn, NY 11201 USA

来源：

1998 IEEE SECOND WORKSHOP ON MULTIMEDIA SIGNAL PROCESSING | 1998年

关键词：

D O I：

10.1109/MMSP.1998.738908

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

This paper describes a technique for classifying TV broadcast video using Hidden Markov Model (HMM) [1]. Here we consider the problem of discriminating five types of TV programs, namely commercials, basketball games, football games, news reports, and weather forecasts. Eight frame-based audio features are used to characterize the low-level audio properties, and fourteen clip-based audio features are extracted based on these frame-based features to characterize the high-level audio properties. For each type of these five TV programs, we build an erg;odic HMM using the clip-based features as observation vectors. The maximum likelihood method is then used for classifying testing data using the trained models.

引用

页码：27 / 32

页数：6