Learned Color Constancy From Local Correspondences

Tijmen Moerland 1, 2 Frédéric Jurie 1
1 LEAR - Learning and recognition in vision
GRAVIR - IMAG - Graphisme, Vision et Robotique, Inria Grenoble - Rhône-Alpes, CNRS - Centre National de la Recherche Scientifique : FR71
Abstract : The ability of humans for color constancy, i.e. the ability to correct for color deviation caused by a different illumination, is far beyond computer vision performances: nowadays, automatic color constancy is still a difficult problem. This article proposes a new step forward towards solving this color constancy problem. Basically, it consists in learning how illumination can affect some reference objects. During a learning stage, images are taken under various illuminations, allowing for automatic building of a model explaining color changes. The model can explain complex non-linear color transformations with only a few parameters. Therefore, the observation of color variations in a few reference regions (e.g. known object) is enough to estimate the global color changes.
Document type :
Conference papers
Complete list of metadatas

https://hal.inria.fr/inria-00548507
Contributor : Thoth Team <>
Submitted on : Monday, December 20, 2010 - 9:07:36 AM
Last modification on : Tuesday, June 5, 2018 - 6:00:02 PM

Links full text

Identifiers

Collections

IMAG | INRIA | UGA

Citation

Tijmen Moerland, Frédéric Jurie. Learned Color Constancy From Local Correspondences. IEEE International Conference on Multimedia and Expo (ICME '05), Jul 2005, Amsterdam, Netherlands. pp.820-823, ⟨10.1109/ICME.2005.1521549⟩. ⟨inria-00548507⟩

Share

Metrics

Record views

153