loading
Papers

Research.Publish.Connect.

Paper

Authors: Yanlin Qian 1 ; Said Pertuz 2 ; Jarno Nikkanen 3 ; Joni-Kristian Kämäräinen 2 and Jiri Matas 4

Affiliations: 1 Laboratory of Signal Processing, Tampere University of Technology, Finland, Center for Machine Perception, Czech Technical University in Prague and Czech Republic ; 2 Laboratory of Signal Processing, Tampere University of Technology and Finland ; 3 Intel Finland and Finland ; 4 Center for Machine Perception, Czech Technical University in Prague and Czech Republic

ISBN: 978-989-758-354-4

Keyword(s): Illumination Estimation, Color Constancy, Gray Pixel.

Related Ontology Subjects/Areas/Topics: Applications and Services ; Color and Texture Analyses ; Computational Photography ; Computer Vision, Visualization and Computer Graphics ; Digital Photography ; Image and Video Analysis ; Image Formation and Preprocessing ; Image Formation, Acquisition Devices and Sensors ; Rendering

Abstract: We present a statistical color constancy method that relies on novel gray pixel detection and mean shift clustering. The method, called Mean Shifted Grey Pixel – MSGP, is based on the observation: true-gray pixels are aligned towards one single direction. Our solution is compact, easy to compute and requires no training. Experiments on two real-world benchmarks show that the proposed approach outperforms state-of-the-art methods in the camera-agnostic scenario. In the setting where the camera is known, MSGP outperforms all statistical methods.

PDF ImageFull Text

Download
CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 35.172.111.215

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Qian, Y.; Pertuz, S.; Nikkanen, J.; Kämäräinen, J. and Matas, J. (2019). Revisiting Gray Pixel for Statistical Illumination Estimation.In Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4 VISAPP: VISAPP, ISBN 978-989-758-354-4, pages 36-46. DOI: 10.5220/0007406900360046

@conference{visapp19,
author={Yanlin Qian. and Said Pertuz. and Jarno Nikkanen. and Joni{-}Kristian Kämäräinen. and Jiri Matas.},
title={Revisiting Gray Pixel for Statistical Illumination Estimation},
booktitle={Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4 VISAPP: VISAPP,},
year={2019},
pages={36-46},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007406900360046},
isbn={978-989-758-354-4},
}

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4 VISAPP: VISAPP,
TI - Revisiting Gray Pixel for Statistical Illumination Estimation
SN - 978-989-758-354-4
AU - Qian, Y.
AU - Pertuz, S.
AU - Nikkanen, J.
AU - Kämäräinen, J.
AU - Matas, J.
PY - 2019
SP - 36
EP - 46
DO - 10.5220/0007406900360046

Login or register to post comments.

Comments on this Paper: Be the first to review this paper.