DocumentCode :
356993
Title :
TV program classification based on face and text processing
Author :
Wei, Gang ; Agnihotri, Lalitha ; Dimitrova, Nevenka
Author_Institution :
Dept. of Comput. Sci., Wayne State Univ., Detroit, MI, USA
Volume :
3
fYear :
2000
fDate :
2000
Firstpage :
1345
Abstract :
In this paper we describe a system to classify TV programs into predefined categories based on the analysis of their video contents. This is very useful in intelligent display and storage systems that can select channels and record or skip contents according to the consumer´s preference. Distinguishable patterns exist in different categories of TV programs in terms of human faces and superimposed text. By applying face and text tracking to a number of training video segments, including commercials, news, sitcoms, and soaps, we have identified patterns within each category of TV programs in a predefined feature space that reflects the face and text characteristics of the video. A given video segment is projected to the feature space and compared against the distribution of known categories of TV programs. Domain-knowledge is used to help the classification. Encouraging results have been achieved so far in our initial experiments
Keywords :
face recognition; feature extraction; image classification; text analysis; tracking; video signal processing; TV program classification; channel selection; content recording; content skipping; domain knowledge; face processing; face tracking; human faces; intelligent display systems; intelligent storage systems; superimposed text; text processing; text tracking; training video segments; video content analysis; Computer displays; Computer science; Data mining; Face detection; Humans; Proposals; Switches; TV; Text processing; Watches;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Multimedia and Expo, 2000. ICME 2000. 2000 IEEE International Conference on
Conference_Location :
New York, NY
Print_ISBN :
0-7803-6536-4
Type :
conf
DOI :
10.1109/ICME.2000.871015
Filename :
871015
Link To Document :
بازگشت