Edge-moment-based color constancy using illumination-coherent regularized regression

Considering no previous literature reveals the effectiveness of image similarity coherent with corresponding illuminant in color constancy, we propose an edge-moment-based algorithm using regularized regression in an illumination-coherent space in a divide-and-conquer way. To represent the scene images, we adopt color edge moments which are then projected into an illumination-coherent space using canonical correlation analysis (CCA). Further, a mixture of Gaussians (MoG) model is exploited to construct consistent subspaces, in each of which an iterative l₂-norm regularized regression is used to learn the correlation between edge moments and illuminants. In the testing phase, estimations from each subspace are fused in a soft way according to the posterior possibility of the test image caused by the MoG. Extensive experiments on the standard datasets including the intra- and inter-dataset evaluations show that our approach outperforms the state-of-the-art algorithms.