Presentation 2006/1/3
THE CLASSIFICATION TECHNIQUE USING THE COMPOSITION OF PHOTOGRAPHS FOR KANSEI RETRIEVAL(International Workshop on Advanced Image Technology 2006)
Hitoshi Kuriyama, Kunio Kondo,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) With the spread of digital cameras, it is now easy for anyone to take a large number of photographs, which can be accumulated as image data in personal computers. There is a growing expectation that these photographs can be efficiently managed and retrieved. In each photograph the composition is a factor which produces an impression and there is a pattern in the composition where the viewer feels the picture is stable and well-balanced. A professional cameraman has a detailed knowledge of composition, and various impressions can be given by combining compositions. For example, the Triangular composition imparts a sense of stability, and a feeling of a lively motion is expressed in the Diagonal composition. In this research, we propose a technique for extracting compositional information from photographic images and applying the difference in the impression gained from the composition to KANSEI retrieval.
Keyword(in Japanese) (See Japanese page)
Keyword(in English)
Paper # IE2005-204
Date of Issue

Conference Information
Committee IE
Conference Date 2006/1/3(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 Image Engineering (IE)
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) THE CLASSIFICATION TECHNIQUE USING THE COMPOSITION OF PHOTOGRAPHS FOR KANSEI RETRIEVAL(International Workshop on Advanced Image Technology 2006)
Sub Title (in English)
Keyword(1)
1st Author's Name Hitoshi Kuriyama
1st Author's Affiliation Saitama University()
2nd Author's Name Kunio Kondo
2nd Author's Affiliation Saitama University
Date 2006/1/3
Paper # IE2005-204
Volume (vol) vol.105
Number (no) 501
Page pp.pp.-
#Pages 6
Date of Issue