Color Constancy Using KL-Divergence
Abstract
Color is a useful feature for machine vision tasks. However its effectiveness is often limited by the fact that the measured pixel values in a scene are influenced by both object surface reflectance properties and incident illumination. Color constancy algorithms attempt to compute color features which are invariant of the incident illumination by estimating the parameters of the global scene illumination and factoring out its effect. A number of recently developed algorithms utilize statistical methods to estimate the maximum likelihood values of the illumination parameters. This paper details the use of KL-divergence as a means of selecting estimated illumination parameter values. We provide experimental results demonstrating the usefulness of the KL-divergence technique for accurately estimating the global illumination parameters of real world images.
Cite
Text
Rosenberg et al. "Color Constancy Using KL-Divergence." IEEE/CVF International Conference on Computer Vision, 2001. doi:10.1109/ICCV.2001.10028Markdown
[Rosenberg et al. "Color Constancy Using KL-Divergence." IEEE/CVF International Conference on Computer Vision, 2001.](https://mlanthology.org/iccv/2001/rosenberg2001iccv-color/) doi:10.1109/ICCV.2001.10028BibTeX
@inproceedings{rosenberg2001iccv-color,
title = {{Color Constancy Using KL-Divergence}},
author = {Rosenberg, Charles R. and Hebert, Martial and Thrun, Sebastian},
booktitle = {IEEE/CVF International Conference on Computer Vision},
year = {2001},
pages = {239-246},
doi = {10.1109/ICCV.2001.10028},
url = {https://mlanthology.org/iccv/2001/rosenberg2001iccv-color/}
}