A VLSI Neural Network for Color Constancy

Creators: Moore, Andrew; Allman, John; Fox, Geoffrey; Goodman, Rodney

Others:: Lippmann, Richard P.; Moody, John E.; Touretzky, David S.

Abstract

A system for color correction has been designed, built, and tested successfully; the essential components are three custom chips built using sub-threshold analog CMOS VLSI. The system, based on Land's Retinex theory 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.

Additional Information

© 1991 Morgan Kaufmann. We are grateful to many of our colleagues at Cal tech and elsewhere for discussions and support in this endeavor. A.M. was supported by fellowships from the Parsons Foundation and the Pew Charitable Trust and by research assistantships from Office of Naval Research, the Joint Tactical Fusion Program and the Center for Research in Parallel Computation. We are grateful to DARPA for MOSIS fabrication services, and to Hewlett Packard for computing support in the Mead Lab. The California Institute of Technology has filed for a U.S. patent for this and other related work.

Attached Files

Published - 396-a-vlsi-neural-network-for-color-constancy.pdf

Files

396-a-vlsi-neural-network-for-color-constancy.pdf

Files (1.8 MB)

Name	Size	Download all
396-a-vlsi-neural-network-for-color-constancy.pdf md5:42863b394f69116a0a66c5ef20604310	1.8 MB	Preview Download

Additional details

	All versions	This version
Views	0	0
Downloads	0	0
Data volume	0 Bytes	0 Bytes