Tampere University of Technology

TUTCRIS Research Portal

A Dataset for Camera Independent Color Constancy

Research output: Contribution to journalArticleScientificpeer-review

Standard

A Dataset for Camera Independent Color Constancy. / Aytekin, Caglar; Nikkanen, Jarno; Gabbouj, Moncef.

In: IEEE Transactions on Image Processing, Vol. 27, No. 2, 2018, p. 530-544.

Research output: Contribution to journalArticleScientificpeer-review

Harvard

Aytekin, C, Nikkanen, J & Gabbouj, M 2018, 'A Dataset for Camera Independent Color Constancy', IEEE Transactions on Image Processing, vol. 27, no. 2, pp. 530-544. https://doi.org/10.1109/TIP.2017.2764264

APA

Aytekin, C., Nikkanen, J., & Gabbouj, M. (2018). A Dataset for Camera Independent Color Constancy. IEEE Transactions on Image Processing, 27(2), 530-544. https://doi.org/10.1109/TIP.2017.2764264

Vancouver

Aytekin C, Nikkanen J, Gabbouj M. A Dataset for Camera Independent Color Constancy. IEEE Transactions on Image Processing. 2018;27(2):530-544. https://doi.org/10.1109/TIP.2017.2764264

Author

Aytekin, Caglar ; Nikkanen, Jarno ; Gabbouj, Moncef. / A Dataset for Camera Independent Color Constancy. In: IEEE Transactions on Image Processing. 2018 ; Vol. 27, No. 2. pp. 530-544.

Bibtex - Download

@article{4d4836de626d441cb3b26e34f63ee8a7,
title = "A Dataset for Camera Independent Color Constancy",
abstract = "In this paper, we provide a novel dataset designed for camera independent color constancy research. Camera independence corresponds to the robustness of an algorithm’s performance when run on images of the same scene taken by different cameras. Accordingly, the images in our database correspond to several lab and field scenes each of which is captured by three different cameras with minimal registration errors. The lab scenes are also captured under five different illuminations. The spectral responses of cameras and the spectral power distributions of the lab light sources are also provided, as they may prove beneficial for training future algorithms to achieve color constancy. For a fair evaluation of future methods, we provide guidelines for supervised methods with indicated training, validation and testing partitions. Accordingly, we evaluate two recently proposed convolutional neural network based color constancy algorithms as baselines for future research. As a side contribution, this dataset also includes images taken by a mobile camera with color shading corrected and uncorrected results. This allows research on the effect of color shading as well.",
keywords = "Cameras, Color constancy, color shading, illumination estimation, Image color analysis, Lighting, platform independence, Reflectivity, Robustness, Sensitivity, Training",
author = "Caglar Aytekin and Jarno Nikkanen and Moncef Gabbouj",
year = "2018",
doi = "10.1109/TIP.2017.2764264",
language = "English",
volume = "27",
pages = "530--544",
journal = "IEEE Transactions on Image Processing",
issn = "1057-7149",
publisher = "Institute of Electrical and Electronics Engineers",
number = "2",

}

RIS (suitable for import to EndNote) - Download

TY - JOUR

T1 - A Dataset for Camera Independent Color Constancy

AU - Aytekin, Caglar

AU - Nikkanen, Jarno

AU - Gabbouj, Moncef

PY - 2018

Y1 - 2018

N2 - In this paper, we provide a novel dataset designed for camera independent color constancy research. Camera independence corresponds to the robustness of an algorithm’s performance when run on images of the same scene taken by different cameras. Accordingly, the images in our database correspond to several lab and field scenes each of which is captured by three different cameras with minimal registration errors. The lab scenes are also captured under five different illuminations. The spectral responses of cameras and the spectral power distributions of the lab light sources are also provided, as they may prove beneficial for training future algorithms to achieve color constancy. For a fair evaluation of future methods, we provide guidelines for supervised methods with indicated training, validation and testing partitions. Accordingly, we evaluate two recently proposed convolutional neural network based color constancy algorithms as baselines for future research. As a side contribution, this dataset also includes images taken by a mobile camera with color shading corrected and uncorrected results. This allows research on the effect of color shading as well.

AB - In this paper, we provide a novel dataset designed for camera independent color constancy research. Camera independence corresponds to the robustness of an algorithm’s performance when run on images of the same scene taken by different cameras. Accordingly, the images in our database correspond to several lab and field scenes each of which is captured by three different cameras with minimal registration errors. The lab scenes are also captured under five different illuminations. The spectral responses of cameras and the spectral power distributions of the lab light sources are also provided, as they may prove beneficial for training future algorithms to achieve color constancy. For a fair evaluation of future methods, we provide guidelines for supervised methods with indicated training, validation and testing partitions. Accordingly, we evaluate two recently proposed convolutional neural network based color constancy algorithms as baselines for future research. As a side contribution, this dataset also includes images taken by a mobile camera with color shading corrected and uncorrected results. This allows research on the effect of color shading as well.

KW - Cameras

KW - Color constancy

KW - color shading

KW - illumination estimation

KW - Image color analysis

KW - Lighting

KW - platform independence

KW - Reflectivity

KW - Robustness

KW - Sensitivity

KW - Training

U2 - 10.1109/TIP.2017.2764264

DO - 10.1109/TIP.2017.2764264

M3 - Article

VL - 27

SP - 530

EP - 544

JO - IEEE Transactions on Image Processing

JF - IEEE Transactions on Image Processing

SN - 1057-7149

IS - 2

ER -