Hue geometry and horizontal connections

被引:14
作者
Ben-Shahar, O [1 ]
Zucker, SW
机构
[1] Yale Univ, Dept Comp Sci, Interdepartmental Neurosci Program, New Haven, CT 06520 USA
[2] Yale Univ, Dept Biomed Engn, New Haven, CT 06520 USA
基金
美国国家卫生研究院;
关键词
hue curvature; horizontal connection; cytochrome oxidase blobs;
D O I
10.1016/j.neunet.2004.03.011
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Primate visual systems support an elaborate specialization for processing color information. Concentrating on the hue component, we observe that, contrary to Mondrian-like assumptions, hue varies in a smooth manner for ecologically important natural imagery. To represent these smooth variations, and to support those information processing tasks that utilize hue, a piecewise smooth hue field is postulated. The geometry of hue-patch interactions is developed analogously to orientation-patch interactions in texture. The result is a model for long-range (horizontal) interactions in the color domain, the power of which is demonstrated on a number of examples. Implications for computer image processing, computer vision, visual neurophysiology and psychophysics are discussed. (C) 2004 Elsevier Ltd. All rights reserved.
引用
收藏
页码:753 / 771
页数:19
相关论文
共 82 条
[1]  
ALBERS J, 1987, INTERACTION COLOR
[2]  
Allen G., 1879, The Colour-Sense: Its Origin and Development. An Essay in Comparative Psychology
[3]  
ALLMAN J, 1990, COLD SPRING HARB SYM, V55, P979
[4]   VECTOR MEDIAN FILTERS [J].
ASTOLA, J ;
HAAVISTO, P ;
NEUVO, Y .
PROCEEDINGS OF THE IEEE, 1990, 78 (04) :678-689
[5]   Color constancy for scenes with varying illumination [J].
Barnard, K ;
Finlayson, G ;
Funt, B .
COMPUTER VISION AND IMAGE UNDERSTANDING, 1997, 65 (02) :311-321
[6]  
BAXANDLL M, 1995, SHADOWS ENLIGHTENMEN
[7]   How long range is contour integration in human color vision? [J].
Beaudot, WHA ;
Mullen, KT .
VISUAL NEUROSCIENCE, 2003, 20 (01) :51-64
[8]  
Beck J., 1972, Surface Color Perception
[9]  
BELL A, 1997, VISION RES, V37, P2228
[10]   Sensitivity to curvatures in orientation-based texture segmentation [J].
Ben-Shahar, O ;
Zucker, SW .
VISION RESEARCH, 2004, 44 (03) :257-277