Accession Number : ADA184385

Title :   Learning a Color Algorithm from Examples.

Descriptive Note : Memorandum rept.,

Corporate Author : MASSACHUSETTS INST OF TECH CAMBRIDGE ARTIFICIAL INTELLIGENCE LAB

Personal Author(s) : Hurlbert,Anya ; Poggio,Tomaso

PDF Url : ADA184385

Report Date : Jun 1987

Pagination or Media Count : 32

Abstract : 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.

Descriptors :   *ALGORITHMS, *IMAGE PROCESSING, *LEARNING, *VISUAL PERCEPTION, *COLOR VISION, PROBLEM SOLVING, COMPUTATIONS, INFORMATION PROCESSING, ARTIFICIAL INTELLIGENCE

Subject Categories : Anatomy and Physiology
      Numerical Mathematics
      Bionics

Distribution Statement : APPROVED FOR PUBLIC RELEASE