Combining physical and statistical evidence for computational colour constancy

Colour constancy algorithms are typically divided into physics-based techniques which exploit the physical image formation process and statistics-based method that use statistical knowledge on surfaces and lights. In this paper we introduce a combined physical and statistical algorithm for computational colour constancy. Estimates obtained from the statistical Colour by Correlation algorithm are integrated with those of a physics based method based on the dichromatic reflectance model. The algorithm not only provides an illuminant estimate but a complete set of likelihoods for a given set of reference lights. Recovery performance is shown to exceed that of purely statistical and purely physical algorithms.