Learning color constancy

Brian Funt, Vlad Cardei, Jacobus J Barnard

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

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)
Title of host publicationProceedings of the Color Imaging Conference: Color Science, Systems, and Applications
Editors Anon
PublisherSoc Imaging Sci Technol
Pages58-60
Number of pages3
StatePublished - 1997
Externally publishedYes
EventProceedings of the 1996 4th Color Imaging Conference Color Science, Science, and Applications - Scottsdale, AZ, USA
Duration: Nov 19 1996Nov 22 1996

Other

OtherProceedings of the 1996 4th Color Imaging Conference Color Science, Science, and Applications
CityScottsdale, AZ, USA
Period11/19/9611/22/96

Fingerprint

Lighting
Color
Neural networks
Cameras

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Funt, B., Cardei, V., & Barnard, J. J. (1997). Learning color constancy. In Anon (Ed.), Proceedings of the Color Imaging Conference: Color Science, Systems, and Applications (pp. 58-60). Soc Imaging Sci Technol.

Learning color constancy. / Funt, Brian; Cardei, Vlad; Barnard, Jacobus J.

Proceedings of the Color Imaging Conference: Color Science, Systems, and Applications. ed. / Anon. Soc Imaging Sci Technol, 1997. p. 58-60.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Funt, B, Cardei, V & Barnard, JJ 1997, Learning color constancy. in Anon (ed.), Proceedings of the Color Imaging Conference: Color Science, Systems, and Applications. Soc Imaging Sci Technol, pp. 58-60, Proceedings of the 1996 4th Color Imaging Conference Color Science, Science, and Applications, Scottsdale, AZ, USA, 11/19/96.
Funt B, Cardei V, Barnard JJ. Learning color constancy. In Anon, editor, Proceedings of the Color Imaging Conference: Color Science, Systems, and Applications. Soc Imaging Sci Technol. 1997. p. 58-60
Funt, Brian ; Cardei, Vlad ; Barnard, Jacobus J. / Learning color constancy. Proceedings of the Color Imaging Conference: Color Science, Systems, and Applications. editor / Anon. Soc Imaging Sci Technol, 1997. pp. 58-60
@inproceedings{0a3800c558b24222b2cd1846816c5776,
title = "Learning color constancy",
abstract = "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.",
author = "Brian Funt and Vlad Cardei and Barnard, {Jacobus J}",
year = "1997",
language = "English (US)",
pages = "58--60",
editor = "Anon",
booktitle = "Proceedings of the Color Imaging Conference: Color Science, Systems, and Applications",
publisher = "Soc Imaging Sci Technol",

}

TY - GEN

T1 - Learning color constancy

AU - Funt, Brian

AU - Cardei, Vlad

AU - Barnard, Jacobus J

PY - 1997

Y1 - 1997

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=0031364175&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031364175&partnerID=8YFLogxK

M3 - Conference contribution

SP - 58

EP - 60

BT - Proceedings of the Color Imaging Conference: Color Science, Systems, and Applications

A2 - Anon, null

PB - Soc Imaging Sci Technol

ER -