Presentation 2009-03-13
Event Classification of Sport News Photos by Integrating Textual and Visual Features
AKIO KITAHARA, KEIJI YANAI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) There are many Web news sites which deliver us news photos everyday. However, since they classified news photos only very roughly, it is not easy for us to search for photos we want from a huge amount of news photos. In this paper, we treat with event classification of sports news photos as an instance of researches on more sophisticated search methods for large-scale photo news databases. We propose two methods to classify sports news photos into one of six sports genres and to discriminate in-play photos from not-in-play ones. One is the two-step method which classifies sport genres first and recognizes in-play conditions next, and the other is the two-step method which classifies them simultaneously. In the proposed methods, we integrate textual features extracted from news articles and image features extracted from photo images by Multiple Kernel Learning (MKL). In the experiment of the two-step method, we obtained 99.33% as the classification rate for the genre classification which is the first step and 80.75% for the in-play classification which is the second step. On the other hand, in the experiment of the one-step method, we obtained 77.08% which was a little less than the result by the two-step method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English)
Paper # PRMU2008-257
Date of Issue

Conference Information
Committee PRMU
Conference Date 2009/3/6(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 Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Event Classification of Sport News Photos by Integrating Textual and Visual Features
Sub Title (in English)
Keyword(1)
1st Author's Name AKIO KITAHARA
1st Author's Affiliation Department of Computer Science, The University of Electro-Communications()
2nd Author's Name KEIJI YANAI
2nd Author's Affiliation Department of Computer Science, The University of Electro-Communications
Date 2009-03-13
Paper # PRMU2008-257
Volume (vol) vol.108
Number (no) 484
Page pp.pp.-
#Pages 8
Date of Issue