Improving color correction across camera and illumination changes by contextual sample selection

Abstract : In many tasks of machine vision applications, it is important that recorded colors remain constant, in the real world scene, even under changes of the illuminants and the cameras. Contrary to the human vision system, a machine vision system exhibits inadequate adaptability to the variation of lighting conditions. Automatic white bal- ance control available in commercial cameras is not sufficient to pro- vide reproducible color classification. We address this problem of color constancy on a large image database acquired with varying digi- tal cameras and lighting conditions. A device-independent color repre- sentation may be obtained by applying a chromatic adaptation transform, from a calibrated color checker pattern included in the field of view. Instead of using the standard Macbeth color checker, we suggest selecting judicious colors to design a customized pattern from contextual information. A comparative study demonstrates that this approach ensures a stronger constancy of the colors-of- interest before vision control thus enabling a wide variety of applica- tions.
Liste complète des métadonnées

Cited literature [28 references]  Display  Hide  Download

https://hal-univ-bourgogne.archives-ouvertes.fr/hal-00719790
Contributor : Alamin Mansouri <>
Submitted on : Friday, July 20, 2012 - 8:49:43 PM
Last modification on : Thursday, February 21, 2019 - 10:52:51 AM
Document(s) archivé(s) le : Sunday, October 21, 2012 - 3:31:03 AM

File

Wannous-JEI_revised.pdf
Files produced by the author(s)

Identifiers

Citation

Hazem Wannous, Yves Lucas, Sylvie Treuillet, Alamin Mansouri, Yvon Voisin. Improving color correction across camera and illumination changes by contextual sample selection. Journal of Electronic Imaging, SPIE and IS&T, 2012, 21 (2), pp.023015-1--023015-14. ⟨10.1117/1.JEI.21.2.023015⟩. ⟨hal-00719790⟩

Share

Metrics

Record views

679

Files downloads

2378