A VLSI Neural Network for Color Constancy

Part of Advances in Neural Information Processing Systems 3 (NIPS 1990)

Bibtex Metadata Paper

Authors

Andrew Moore, John Allman, Geoffrey Fox, Rodney Goodman

Abstract

A system for color correction has been designed, built, and tested suc(cid:173) cessfully; the essential components are three custom chips built using sub(cid:173) threshold analog CMOS VLSI. The system, based on Land's Retinex the(cid:173) ory of color constancy, produces colors similar in many respects to those produced by the visual system. Resistive grids implemented in analog VLSI perform the smoothing operation central to the algorithm at video rates. With the electronic system, the strengths and weaknesses of the algorithm are explored.

1 A MODEL FOR COLOR CONSTANCY

Humans have the remarkable ability to perceive object colors as roughly constant even if the color of the illumination is varied widely. Edwin Land, founder of the Polaroid Corporation, models the computation that results in this ability as three identical center-surround operations performed independently in three color planes, such as red, green, and blue (Land, 1986). The basis for this model is as follows.

Consider first an array of grey papers with different reflectances. (Land designated these arrays Mondrians, since they resemble the works of the Dutch painter Piet

·Present address: Dept. of Physics, Syracuse University, Syracuse, NY 13244