A Categorical Perception Model in consideration for Color Constancy (Medical Imaging and Computer Vision)(International Workshop On Advanced Image Technology (IWAIT2004))

概要

論文の詳細を見る
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.
社団法人電子情報通信学会の論文
2004-01-06