Multiple illuminant estimation from the covariance of colors

In this paper we present a single and a multiple illuminant estimation physics-based algorithm. Both algorithms are based on the mean projections maximization assumption and un-centered component analysis. The proposed assumption is validated for a large collection of images and later used to estimate the illuminant color. The multiple illuminant estimator assumes that the spectral power distribution of the light source is not the same for the whole scene, which is the case for a wide range of images. In such cases, our new multiple illuminant estimator recovers an accurate illuminants estimates map for each input image while maintaining speed. The evaluation of the proposed algorithms on different real image datasets is realized. The experimental results are satisfying; our algorithms maximize the trade-off between accuracy (illuminant estimation error) and computational complexity.