A Multistage Neural Network for Color Constancy and Color Induction

Susan M. Courtney; Leif H. Finkel; Gershon Buchsbaum

doi:10.1109/72.392259

A Multistage Neural Network for Color Constancy and Color Induction

Susan M. Courtney, Leif H. Finkel, Gershon Buchsbaum

Research output: Contribution to journal › Article › peer-review

Abstract

The network takes advantage of several mechanisms in the human visual system, including retinal adaptation, spectral opponency, and spectrally-specific long-range inhibition. This last stage is a novel mechanism based on cells which have been described in cortical area V4. All stages include nonlinear response functions. The model emulates human performance in several psychophysical paradigms designed to test color constancy and color induction. We measured the amount of constancy achieved with both natural and artificial simulated illuminants, using homogeneous grey backgrounds and more complex backgrounds, such as Mondrians. On average, the model performs as well or better than the average human color constancy performance under similar conditions. The network simulation also displays color induction and assimilation behavior consistent with human perceptual data. A biologically-based multistage neural network is presented which produces color constant responses to a variety of color stimuli.

Original language	English (US)
Pages (from-to)	972-985
Number of pages	14
Journal	IEEE Transactions on Neural Networks
Volume	6
Issue number	4
DOIs	https://doi.org/10.1109/72.392259
State	Published - Jul 1995
Externally published	Yes

ASJC Scopus subject areas

Software
Computer Science Applications
Computer Networks and Communications
Artificial Intelligence

Access to Document

10.1109/72.392259

Fingerprint Dive into the research topics of 'A Multistage Neural Network for Color Constancy and Color Induction'. Together they form a unique fingerprint.

Cite this

@article{d3cf29cf75a24777a8db3b6e7f73ebce,

title = "A Multistage Neural Network for Color Constancy and Color Induction",

abstract = "The network takes advantage of several mechanisms in the human visual system, including retinal adaptation, spectral opponency, and spectrally-specific long-range inhibition. This last stage is a novel mechanism based on cells which have been described in cortical area V4. All stages include nonlinear response functions. The model emulates human performance in several psychophysical paradigms designed to test color constancy and color induction. We measured the amount of constancy achieved with both natural and artificial simulated illuminants, using homogeneous grey backgrounds and more complex backgrounds, such as Mondrians. On average, the model performs as well or better than the average human color constancy performance under similar conditions. The network simulation also displays color induction and assimilation behavior consistent with human perceptual data. A biologically-based multistage neural network is presented which produces color constant responses to a variety of color stimuli.",

author = "Courtney, {Susan M.} and Finkel, {Leif H.} and Gershon Buchsbaum",

note = "Funding Information: Manuscript received July 26, 1993, revised March 28, 1994. This work was supported by ONR Grants ”14-93-1-0681, AFOSR Grants NL 91-0082 and 92-5-0316. and grants from The Whitaker Foundation, and The McDonnell-Pew Program in Cognitive Neuroscience. Copyright: Copyright 2015 Elsevier B.V., All rights reserved.",

year = "1995",

month = jul,

doi = "10.1109/72.392259",

language = "English (US)",

volume = "6",

pages = "972--985",

journal = "IEEE Transactions on Neural Networks and Learning Systems",

issn = "2162-237X",

publisher = "IEEE Computational Intelligence Society",

number = "4",

}

TY - JOUR

T1 - A Multistage Neural Network for Color Constancy and Color Induction

AU - Courtney, Susan M.

AU - Finkel, Leif H.

AU - Buchsbaum, Gershon

N1 - Funding Information: Manuscript received July 26, 1993, revised March 28, 1994. This work was supported by ONR Grants ”14-93-1-0681, AFOSR Grants NL 91-0082 and 92-5-0316. and grants from The Whitaker Foundation, and The McDonnell-Pew Program in Cognitive Neuroscience. Copyright: Copyright 2015 Elsevier B.V., All rights reserved.

PY - 1995/7

Y1 - 1995/7

N2 - The network takes advantage of several mechanisms in the human visual system, including retinal adaptation, spectral opponency, and spectrally-specific long-range inhibition. This last stage is a novel mechanism based on cells which have been described in cortical area V4. All stages include nonlinear response functions. The model emulates human performance in several psychophysical paradigms designed to test color constancy and color induction. We measured the amount of constancy achieved with both natural and artificial simulated illuminants, using homogeneous grey backgrounds and more complex backgrounds, such as Mondrians. On average, the model performs as well or better than the average human color constancy performance under similar conditions. The network simulation also displays color induction and assimilation behavior consistent with human perceptual data. A biologically-based multistage neural network is presented which produces color constant responses to a variety of color stimuli.

AB - The network takes advantage of several mechanisms in the human visual system, including retinal adaptation, spectral opponency, and spectrally-specific long-range inhibition. This last stage is a novel mechanism based on cells which have been described in cortical area V4. All stages include nonlinear response functions. The model emulates human performance in several psychophysical paradigms designed to test color constancy and color induction. We measured the amount of constancy achieved with both natural and artificial simulated illuminants, using homogeneous grey backgrounds and more complex backgrounds, such as Mondrians. On average, the model performs as well or better than the average human color constancy performance under similar conditions. The network simulation also displays color induction and assimilation behavior consistent with human perceptual data. A biologically-based multistage neural network is presented which produces color constant responses to a variety of color stimuli.

UR - http://www.scopus.com/inward/record.url?scp=0029345901&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029345901&partnerID=8YFLogxK

U2 - 10.1109/72.392259

DO - 10.1109/72.392259

M3 - Article

C2 - 18263385

AN - SCOPUS:0029345901

VL - 6

SP - 972

EP - 985

JO - IEEE Transactions on Neural Networks and Learning Systems

JF - IEEE Transactions on Neural Networks and Learning Systems

SN - 2162-237X

IS - 4

ER -

A Multistage Neural Network for Color Constancy and Color Induction

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Cite this