A manifold based methodology for color constancy

In this paper, we propose a manifold-based methodology for color constancy. It is observed that the center surround information of an image creates a manifold in color space. The relationship between the points in the manifold is modeled as a line. The human visual system is capable of learning these relationships. This is the basis of color constancy. In illumination correction, the image in the reference illumination is operated on with a wide Gaussian function to extract the global illumination information. The global illumination information creates a manifold in color space which is learnt by the system as a line. An image in a different color perception creates a different manifold in color space. To transform the color perception of a scene in a given illumination to the reference color perception, the color relationships in the reference color perception are applied on the new image. This is achieved by projecting the pixels in the new image to the line representing the manifold of reference color perception. This model can be used for color correction of images with different color perceptions to a learnt color perception. This method, unlike other approaches, has a single step convergence and hence is faster.