Chromagenic Colour Constancy

A chromagenic camera takes two pictures of each scene. The first image is taken as normal and then the second is captured with a specially chosen chromagenic filter placed in front of the camera. In contradistinction to previous cameras that have more than 3 sensors, the aim of a chromagenic camera is not to measure more degrees of freedom in reflectance. Indeed, in a chromagenic camera the RGBs are, to a first approximation, linearly related to the filtered RGBs. However, the chromagenic filter is chosen so that this relationship depends on, and varies with illumination. The chromagenic camera is sensitive to the degrees of freedom in illumination. Chromagenic colour constancy proceeds in two stages. In pre-processing, for each light, the relation that takes filtered to unfiltered RGBs is computed. The input to colour constancy processing comprises the unfiltered and filtered RGBs captured for a given scene under unknown lighting conditions. To estimate the illuminant, the filtered responses are transformed by the pre-computed relations, and then these estimates are compared to the unfiltered counterparts. The transform that best predicts the data identifies the illuminant. Remarkably, this very simple approach works as well as, or better than, all other algorithms tested.