Back to articles
Articles
Volume: 7 | Article ID: art00059
Image
Committee-Based Color Constancy
Vlad C. Cardei
Brian Funt
  DOI :  10.2352/CIC.1999.7.1.art00059  Published Online :  January 1999
Abstract

We show how to achieve better illumination estimates for color constancy by combining the results of several existing algorithms. We consider committee methods based on both linear and non–linear ways of combining the illumination estimates from the original set of color constancy algorithms. Committees of grayworld, white patch and neural net methods are tested. The committee results are always more accurate than the estimates of any of the other algorithms taken in isolation.

Journal Title : Color and Imaging Conference
Publisher Name : Society of Imaging Science and Technology
Publisher Location : 7003 Kilworth Lane, Springfield, VA 22151, USA
Subject Areas :
Views 9
Downloads 0
 DOI 10.2352/CIC.1999.7.1.art00059
 articleview.views 9
 articleview.downloads 0
  Cite this article 

Vlad C. Cardei, Brian Funt, "Committee-Based Color Constancy"  in Proc. IS&T 7th Color and Imaging Conf.,  1999,  pp 311 - 313,  https://doi.org/10.2352/CIC.1999.7.1.art00059

 Copy citation
  Copyright statement 
Copyright © Society for Imaging Science and Technology 1999
72010350
Color and Imaging Conference
color imaging conf
2166-9635
Society of Imaging Science and Technology
7003 Kilworth Lane, Springfield, VA 22151, USA
2166-9635(19990101)1999:1L.311;1-
cic_v1999n1/splitsection59.xml
/ist/cic/1999/00001999/00000001/art00059
Articles
Committee-Based Color Constancy
CardeiVlad C.
FuntBrian
01011999
1999
1
311
313
1999
We show how to achieve better illumination estimates for color constancy by combining the results of several existing algorithms. We consider committee methods based on both linear and non–linear ways of combining the illumination estimates from the original set of color constancy algorithms. Committees of grayworld, white patch and neural net methods are tested. The committee results are always more accurate than the estimates of any of the other algorithms taken in isolation.