Presentation 2004-12-09
Content Classification Using Photographic Subject's Position
Manabu ITO, Mayumi KOIKE, Kayo IKEDA, Soichiro HIDAKA, Terumasa AOKI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In recent years, the high spec. PC and large scale HDD appear, and digital contents are continuing the explosive increase. The reference technology for under these circumstances looking for the contents accumulated in large quantities efficiently attracts attention. However, it cannot be said that the efficient reference technique is still enough. The polysemy which each contents have is thought as this factor. This report describes the classification for narrowing down a candidate picture by considering improvement in reference efficiency as the with-kindly-tolerance mark. It is the taxonomy, which combined a parameter called the height and angle of a camera with a photographic subject's position information recognized in common than man's experience value. Moreover, the amount expression of the features using the parameter is also described.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Image Classification / Image/Video Retrieval / Depth Information / Retrieval Query
Paper # CS2004-103,IE2004-98
Date of Issue

Conference Information
Committee CS
Conference Date 2004/12/2(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 Communication Systems (CS)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Content Classification Using Photographic Subject's Position
Sub Title (in English)
Keyword(1) Image Classification
Keyword(2) Image/Video Retrieval
Keyword(3) Depth Information
Keyword(4) Retrieval Query
1st Author's Name Manabu ITO
1st Author's Affiliation The University of Tokyo RCAST()
2nd Author's Name Mayumi KOIKE
2nd Author's Affiliation Espalier
3rd Author's Name Kayo IKEDA
3rd Author's Affiliation Excelled Technology
4th Author's Name Soichiro HIDAKA
4th Author's Affiliation National Institute of Informatics
5th Author's Name Terumasa AOKI
5th Author's Affiliation The University of Tokyo RCAST
Date 2004-12-09
Paper # CS2004-103,IE2004-98
Volume (vol) vol.104
Number (no) 493
Page pp.pp.-
#Pages 6
Date of Issue