CaltechAUTHORS
  A Caltech Library Service

A real-time neural system for color constancy

Moore, Andrew and Allman, John and Goodman, Rodney M. (1991) A real-time neural system for color constancy. IEEE Transactions on Neural Networks, 2 (2). pp. 237-247. ISSN 1045-9227. http://resolver.caltech.edu/CaltechAUTHORS:20170408-172537077

[img] PDF - Published Version
See Usage Policy.

1297Kb

Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:20170408-172537077

Abstract

A neural network approach to the problem of color constancy is presented. Various algorithms based on Land's retinex theory are discussed with respect to neurobiological parallels, computational efficiency, and suitability for VLSI implementation. The efficiency of one algorithm is improved by the application of resistive grids and is tested in computer simulations; the simulations make clear the strengths and weaknesses of the algorithm. A novel extension to the algorithm is developed to address its weaknesses. An electronic system that is based on the original algorithm and that operates at video rates was built using subthreshold analog CMOS VLSI resistive grids. The system displays color constancy abilities and qualitatively mimics aspects of human color perception.


Item Type:Article
Related URLs:
URLURL TypeDescription
http://dx.doi.org/10.1109/72.80334DOIArticle
Additional Information:© 1991 IEEE. Manuscript received August 13, 1990; revised November 21, 1990. This work was supported (via fellowships to A. Moore) by the Parsons Foundation and the Pew Charitable Trust and (via research assistantships) by the Office of Naval Research, the Joint Tactical Fusion Program, and the Center for Research in Parallel Computation. The authors are grateful to many of our colleagues at Caltech and elsewhere for discussions and support in this endeavor: G. Fox, F. Perez, and S. Shein for discussions about color constancy; M. Mahowald, C. Mead, and M. Sivilotti, inventors of the original silicon retina, for systems and VLSI discussions; J. Hams, J. Luo, and C. Koch for discussions about resistive grids; D. Lyon, M. Mahowald, and S. Ryckebush for discussions about sample-and-hold circuitry; J. Lazzaro for discussions on systems issues; and s. Chascsa, T. Horiuchi, and F. Perez for assistance with photography. The authors express their gratitude to DARPA for MOSIS fabrication services, and to Hewlett Packard for computing support in the Mead Lab.
Funders:
Funding AgencyGrant Number
Ralph M. Parsons FoundationUNSPECIFIED
Pew Charitable TrustUNSPECIFIED
Office of Naval Research (ONR)UNSPECIFIED
Joint Tactical Fusion OfficeUNSPECIFIED
Center for Research in Parallel ComputationUNSPECIFIED
Record Number:CaltechAUTHORS:20170408-172537077
Persistent URL:http://resolver.caltech.edu/CaltechAUTHORS:20170408-172537077
Official Citation:A. Moore, J. Allman and R. M. Goodman, "A real-time neural system for color constancy," in IEEE Transactions on Neural Networks, vol. 2, no. 2, pp. 237-247, Mar 1991. doi: 10.1109/72.80334
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:76343
Collection:CaltechAUTHORS
Deposited By: 1Science Import
Deposited On:13 Mar 2018 23:16
Last Modified:13 Mar 2018 23:16

Repository Staff Only: item control page