A parallel algorithm for color constancy

Abstract

Objects retain their color in spite of changes in the wavelength and energy composition of the light they reflect. This phenomenon is called color constancy and plays an important role in computer vision research. We have devised a parallel algorithm for color constancy. The algorithm runs on a two-dimensional grid of processors each of which can exchange information with its four neighboring processors. Each processor calculates local average color. This information is then used to estimate the reflectances of the object. The algorithm was tested on several images of everyday objects. The algorithm also works for scenes where the illuminant changes smoothly over the image. © 2003 Elsevier Inc. All rights reserved.