Color Beaver: Bounding Illumination Estimations for Higher Accuracy

Karlo Koščević, Nikola Banić, Sven Lončarić

2019

Abstract

The image processing pipeline of most contemporary digital cameras performs illumination estimation in order to remove the influence of illumination on image scene colors. In this paper an experiment is described that examines some of the basic properties of illumination estimation methods for several Canon’s camera models. Based on the obtained observations, an extension to any illumination estimation method is proposed that under certain conditions alters the results of the underlying method. It is shown that with statistics-based methods as underlying methods the proposed extension can outperform camera’s illumination estimation in terms of accuracy. This effectively demonstrates that statistics-based methods can still be successfully used for illumination estimation in digital cameras. The experimental results are presented and discussed. The source code is available at https://ipg.fer.hr/ipg/resources/color_constancy.

Paper Citation

in Harvard Style

Koščević K., Banić N. and Lončarić S. (2019). Color Beaver: Bounding Illumination Estimations for Higher Accuracy. In Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 4: VISAPP; ISBN 978-989-758-354-4, SciTePress, pages 183-190. DOI: 10.5220/0007393701830190

in Bibtex Style

@conference{visapp19,
author={Karlo Koščević and Nikola Banić and Sven Lončarić},
title={Color Beaver: Bounding Illumination Estimations for Higher Accuracy},
booktitle={Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 4: VISAPP},
year={2019},
pages={183-190},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007393701830190},
isbn={978-989-758-354-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 4: VISAPP
TI - Color Beaver: Bounding Illumination Estimations for Higher Accuracy
SN - 978-989-758-354-4
AU - Koščević K.
AU - Banić N.
AU - Lončarić S.
PY - 2019
SP - 183
EP - 190
DO - 10.5220/0007393701830190
PB - SciTePress