Color Dog - Guiding the Global Illumination Estimation to Better Accuracy

Nikola Banic, Sven Loncaric

2015

Abstract

An important part of image enhancement is color constancy, which aims to make image colors invariant to illumination. In this paper the Color Dog (CD), a new learning-based global color constancy method is proposed. Instead of providing one, it corrects the other methods’ illumination estimations by reducing their scattering in the chromaticity space by using a its previously learning partition. The proposed method outperforms all other methods on most high-quality benchmark datasets. The results are presented and discussed.

Paper Citation

in Harvard Style

Banic N. and Loncaric S. (2015). Color Dog - Guiding the Global Illumination Estimation to Better Accuracy . In Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2015) ISBN 978-989-758-089-5, pages 129-135. DOI: 10.5220/0005307401290135

in Bibtex Style

@conference{visapp15,
author={Nikola Banic and Sven Loncaric},
title={Color Dog - Guiding the Global Illumination Estimation to Better Accuracy},
booktitle={Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2015)},
year={2015},
pages={129-135},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005307401290135},
isbn={978-989-758-089-5},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2015)
TI - Color Dog - Guiding the Global Illumination Estimation to Better Accuracy
SN - 978-989-758-089-5
AU - Banic N.
AU - Loncaric S.
PY - 2015
SP - 129
EP - 135
DO - 10.5220/0005307401290135