Presentation 2004/1/6
A Categorical Perception Model in consideration for Color Constancy (Medical Imaging and Computer Vision)(International Workshop On Advanced Image Technology (IWAIT2004))
Noriko Yata, Tomoharu Nagao, Keiji Uchikawa,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The purpose of this study is to get a modeling system that can operate similarly to human beings' categorical color perception. Color of object is not determined only by reflection spectrum from the surface of the object alone. It is greatly affected by ambient environmental condition and depends upon color constancy. However, mechanism of color constancy is unexplained. Therefore, it is difficult to acquire cognizance of categorical color name of objects under different illuminations. For this end, the relationship between the chromaticity of color chips under different illuminations and the color chips' categorical color perception under the illumination that is the product of a categorical color naming experiment was learned by a neural network in this paper. Experimental results show that the obtained neural network has the similar characteristics to those of human beings vision system.
Keyword(in Japanese) (See Japanese page)
Keyword(in English)
Paper # IE2003-163
Date of Issue

Conference Information
Committee IE
Conference Date 2004/1/6(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 Image Engineering (IE)
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Categorical Perception Model in consideration for Color Constancy (Medical Imaging and Computer Vision)(International Workshop On Advanced Image Technology (IWAIT2004))
Sub Title (in English)
Keyword(1)
1st Author's Name Noriko Yata
1st Author's Affiliation Yokohama National Univ.()
2nd Author's Name Tomoharu Nagao
2nd Author's Affiliation Yokohama National Univ.
3rd Author's Name Keiji Uchikawa
3rd Author's Affiliation Tokyo Institute of Technology
Date 2004/1/6
Paper # IE2003-163
Volume (vol) vol.103
Number (no) 540
Page pp.pp.-
#Pages 5
Date of Issue