Title :
Biologically-based neural network model of color constancy and color contrast
Author :
Courtney, Susan M. ; Buchsbaum, Gershon ; Finkel, Leif H.
Author_Institution :
Dept. of Bioeng., Pennsylvania Univ., Philadelphia, PA, USA
Abstract :
To determine the surface reflectance of an object independent of the illuminant, a system must use the spatiochromatic context of the image. The authors have developed a neural network model based on the anatomy and physiology of the visual projection from the retina to V4. The network combines color-opponent and contrast information to achieve a good degree of color constancy. This network has been tested on simulated images corresponding to the stimuli used in well established psychophysical experiments. Responses qualitatively matched human responses to a variety of center-surround and Mondrian test stimuli
Keywords :
colour vision; neural nets; visual perception; color constancy; color contrast; psychophysical experiments; Anatomy; Biological system modeling; Layout; Lighting; Neural networks; Physiology; Psychology; Reflectivity; Retina; Testing;
Conference_Titel :
Neural Networks, 1992. IJCNN., International Joint Conference on
Conference_Location :
Baltimore, MD
Print_ISBN :
0-7803-0559-0
DOI :
10.1109/IJCNN.1992.227289