Learning a Color Algorithm from Examples.

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.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 01, 1987
Accession Number
ADA184385

Entities

People

  • Anya Hurlbert
  • Tomaso Poggio

Organizations

  • Massachusetts Institute of Technology

Tags

Communities of Interest

  • Air Platforms
  • Counter IED

DTIC Thesaurus Topics

  • Algorithms
  • Artificial Intelligence
  • Color Vision
  • Computations
  • Equations
  • Illumination
  • Information Processing
  • Information Systems
  • Massachusetts
  • Military Research
  • Physical Properties
  • Psychology
  • Reflectance
  • Reliability
  • Standards
  • Two Dimensional
  • Variational Principles

Fields of Study

  • Computer science

Readers

  • Neural Network Machine Learning.
  • Operations Research
  • Vision Science/Vision Psychology/Cognitive Neuroscience.