Presentation 1997/7/24
Automatic Discrimination of TV Sports News Articles by DCT Features
Yoshiaki SUGIYAMA, Aki SHIBUTANI, Yasuo ARIKI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We are studying about article classification of TV news video by extracting indices from image information after segmenting news video into individual article. Sports news images have some restrictions on objects in their size and position, because of the fixed camera position, so that each category of the sports news has some typical scenes. This fact leads to the automatic classification of sports images using such typical scenes. We have already proposed the scene discrimination algorithm, using a multiple subspace method that provides a category with more than one subspace, based on a whole feature such as DCT features without recognizing the objects in images. In this paper, we report the result of comparison between the proposed multiple subspace method and the vector quantization method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) article discrimination / news video database / subspace method / vector quantization
Paper # MVE97-44
Date of Issue

Conference Information
Committee MVE
Conference Date 1997/7/24(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Media Experience and Virtual Environment (MVE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Automatic Discrimination of TV Sports News Articles by DCT Features
Sub Title (in English)
Keyword(1) article discrimination
Keyword(2) news video database
Keyword(3) subspace method
Keyword(4) vector quantization
1st Author's Name Yoshiaki SUGIYAMA
1st Author's Affiliation Faculty of Science and Technology, Ryukoku University()
2nd Author's Name Aki SHIBUTANI
2nd Author's Affiliation Faculty of Science and Technology, Ryukoku University
3rd Author's Name Yasuo ARIKI
3rd Author's Affiliation Faculty of Science and Technology, Ryukoku University
Date 1997/7/24
Paper # MVE97-44
Volume (vol) vol.97
Number (no) 206
Page pp.pp.-
#Pages 6
Date of Issue