Learning color constancy

Brian Funt, Vlad Cardei, Kobus Barnard

Research output: Contribution to conferencePaperpeer-review

7 Scopus citations


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 chromaticity 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.

Original languageEnglish (US)
Number of pages3
StatePublished - 1997
EventProceedings of the 1996 4th Color Imaging Conference Color Science, Science, and Applications - Scottsdale, AZ, USA
Duration: Nov 19 1996Nov 22 1996


OtherProceedings of the 1996 4th Color Imaging Conference Color Science, Science, and Applications
CityScottsdale, AZ, USA

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition


Dive into the research topics of 'Learning color constancy'. Together they form a unique fingerprint.

Cite this