Learning a Color Algorithm from Examples

摘要

We show that a color algorithm capable of separating illumination from reflectance in a Mondrian world can be learned from a set of examples. The learned algorithm is equivalent to filtering the image data-in which reflectance and illumination are intermixed-through a center-surround receptive field in individual chromatic channels. The operation resembles the retinex algorithm recently proposed by Edwin Land. This result is a specific instance of our earlier result that a standard regularization algorithm can be learned from examples. It illustrates that the natural constraints needed to solve a problem in inverse optics can be extracted directly from a sufficient set of input data and the corresponding solutions. The learning procedure has been implemented as a parallel algorithm on the Connection Machine System.