Colour Constancy Algorithm Based on the Minimization of the Distance between Colour Histograms

descriptionPublicationkeyboard_double_arrow_right Part of book or chapter of book , Conference object , Article 01 Jan 2003 Spain English Publisher:Springer Berlin Heidelberg

Authors: Vergés Llahí, Jaume; Sanfeliu, Alberto;

doi: 10.1007/978-3-540-44871-6_123

handle: 10261/30430

Colour Constancy Algorithm Based on the Minimization of the Distance between Colour Histograms

- Summary
- Subjects
- Metrics

Abstract

Colour is an important clue in many applications in machine vision and image processing. Despite of this, the drwback of color is its dependence upon illumination changes. Coluor constrancy aims to provide colur appearence of objects with stability. This paper presents a simple and robust coluor constrancy algorithm based on a coefficient transformation of the colour coordinates of pixels which goal is to reduce the distance between histograms of two images of similar scenes under different illuminations. Our main contribution is that our algorithm only make use of raw image data contrary to most usual coluor constancy algorithms. We show that our approach is able to cope with the colour change since it substantially reduces the distance between colour histograms.

Partially funded by a fellowship of the Government of Catlonia and tge CICYT DPI2001-2223.

Trabajo presentado al 1st IbPRIA celebrado en Mallorca del 4 al 6 de junio de 2003.

Peer Reviewed

Country

Spain

Related Organizations

Universitat Politècnica de Catalunya
Spain
Spanish National Research Council
Spain

Keywords

Colour histograms, Colour change, Colour constancy, Computer vision, Colours

Impact byBIP!

	selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	2
	popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.	Average
	influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	Average
	impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.	Average