Back to articles
Volume: 4 | Article ID: art00016
Learning Color Constancy
  DOI :  10.2352/CIC.1996.4.1.art00016  Published OnlineJanuary 1996

We decided to test a surprisingly simple hypothesis; namely, that the relationship between an image of a scene and the chromaticity of scene illumination could be learned by a neural network. The thought was that if this relationship could be extracted by a neural network, then the trained network would be able to determine a scene's Illuminant from its image, which would then allow correction of the image colors to those relative to a standard illuminance, thereby providing color constancy. Using a database of surface reflectances and illuminants, along with the spectral sensitivity functions of our camera, we generated thousands of images of randomly selected illuminants lighting ‘scenes’ of 1 to 60 randomly selected reflectances. During the learning phase the network is provided the image data along with the chromaticity of its illuminant. After training, the network outputs (very quickly) the chro-maticity of the illumination given only the image data. We obtained surprisingly good estimates of the ambient illumination lighting from the network even when applied to scenes in our lab that were completely unrelated to the training data.

Subject Areas :
Views 5
Downloads 0
 articleview.views 5
 articleview.downloads 0
  Cite this article 

Brian Funt, Vlad Cardei, Kobus Barnard, "Learning Color Constancyin Proc. IS&T 4th Color and Imaging Conf.,  1996,  pp 58 - 60,

 Copy citation
  Copyright statement 
Copyright © Society for Imaging Science and Technology 1996
Color and Imaging Conference
color imaging conf
Society of Imaging Science and Technology
7003 Kilworth Lane, Springfield, VA 22151, USA