6533b7d2fe1ef96bd125e397

RESEARCH PRODUCT

Design of a customized pattern for improving color constancy across camera and illumination changes

Hazem WannousSylvie TreuilletAlamin MansouriYves LucasYvon Voisin

subject

chromatic adaptationComputer scienceColor normalizationComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONColor balanceField of view02 engineering and technologyVision control[ INFO.INFO-CV ] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]030218 nuclear medicine & medical imaging03 medical and health sciences[INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]0302 clinical medicine0202 electrical engineering electronic engineering information engineeringContextual informationComputer visionColor representationColor constancybusiness.industry[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]Color imagingChromatic adaptationchromatic adaptation.color checker design020201 artificial intelligence & image processingArtificial intelligencebusiness

description

International audience; This paper adresses the problem of color constancy on a large image database acquired with varying digital cameras and lighting conditions. Automatic white balance control proposed by an available commercial camera is not sufficient to provide reproducible color classification. A device-independent color representation 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 to select judicious colors to design a customized pattern from contextual information. A comparative study demonstrates that this approach insures a stronger constancy of the interesting colors before the vision control.

https://hal.archives-ouvertes.fr/hal-00648508/file/Wannous_152.pdf