Biologically-Based Neural Network Model of Color Constancy and Color Contrast

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

doi:10.1109/IJCNN.1992.227289

Biologically-Based Neural Network Model of Color Constancy and Color Contrast

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

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

The light which reaches the eye, or any other sensor, is the product of the reflectance and the illuminant Therefore, in order to determine the surface reflectance of an object independent of the illuminant, a system must use the spatiochromatic context of the image. We have developed a neural network based on the anatomy and physiology of the visual projection from retina to V4. The network combines color-opponent and contrast information to achieve a good degree of color constancy. This network has been tested on simulated images corresponding to the stimuli used in well established psychophysical experiments. Responses qualitatively match human responses to a variety of centersurround and Mondrian test stimuli.

Original language	English (US)
Title of host publication	Proceedings - 1992 International Joint Conference on Neural Networks, IJCNN 1992
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	55-60
Number of pages	6
ISBN (Electronic)	0780305590
DOIs	https://doi.org/10.1109/IJCNN.1992.227289
State	Published - 1992
Externally published	Yes
Event	1992 International Joint Conference on Neural Networks, IJCNN 1992 - Baltimore, United States Duration: Jun 7 1992 → Jun 11 1992

Publication series

Name	Proceedings of the International Joint Conference on Neural Networks
Volume	4

Conference

Conference	1992 International Joint Conference on Neural Networks, IJCNN 1992
Country/Territory	United States
City	Baltimore
Period	6/7/92 → 6/11/92

ASJC Scopus subject areas

Software
Artificial Intelligence

Access to Document

10.1109/IJCNN.1992.227289

Cite this

Courtney, S. M., Buchsbaum, G., & Finkel, L. H. (1992). Biologically-Based Neural Network Model of Color Constancy and Color Contrast. In Proceedings - 1992 International Joint Conference on Neural Networks, IJCNN 1992 (pp. 55-60). (Proceedings of the International Joint Conference on Neural Networks; Vol. 4). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IJCNN.1992.227289

Biologically-Based Neural Network Model of Color Constancy and Color Contrast. / Courtney, Susan M.; Buchsbaum, Gershon; Finkel, Leif H.
Proceedings - 1992 International Joint Conference on Neural Networks, IJCNN 1992. Institute of Electrical and Electronics Engineers Inc., 1992. p. 55-60 (Proceedings of the International Joint Conference on Neural Networks; Vol. 4).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Courtney, SM, Buchsbaum, G & Finkel, LH 1992, Biologically-Based Neural Network Model of Color Constancy and Color Contrast. in Proceedings - 1992 International Joint Conference on Neural Networks, IJCNN 1992. Proceedings of the International Joint Conference on Neural Networks, vol. 4, Institute of Electrical and Electronics Engineers Inc., pp. 55-60, 1992 International Joint Conference on Neural Networks, IJCNN 1992, Baltimore, United States, 6/7/92. https://doi.org/10.1109/IJCNN.1992.227289

Courtney SM, Buchsbaum G, Finkel LH. Biologically-Based Neural Network Model of Color Constancy and Color Contrast. In Proceedings - 1992 International Joint Conference on Neural Networks, IJCNN 1992. Institute of Electrical and Electronics Engineers Inc. 1992. p. 55-60. (Proceedings of the International Joint Conference on Neural Networks). doi: 10.1109/IJCNN.1992.227289

@inproceedings{17b24666de8d4b689fe5ff3a6f356641,

title = "Biologically-Based Neural Network Model of Color Constancy and Color Contrast",

abstract = "The light which reaches the eye, or any other sensor, is the product of the reflectance and the illuminant Therefore, in order to determine the surface reflectance of an object independent of the illuminant, a system must use the spatiochromatic context of the image. We have developed a neural network based on the anatomy and physiology of the visual projection from retina to V4. The network combines color-opponent and contrast information to achieve a good degree of color constancy. This network has been tested on simulated images corresponding to the stimuli used in well established psychophysical experiments. Responses qualitatively match human responses to a variety of centersurround and Mondrian test stimuli.",

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

note = "Funding Information: Supported by grants from the McDonnell-Pew Program in Cognitive Neuroscience, the Whitaker Foundation, AFOSR 91-0082, and ONR N 00014-90-J-1864. Publisher Copyright: {\textcopyright} 1992 IEEE.; 1992 International Joint Conference on Neural Networks, IJCNN 1992 ; Conference date: 07-06-1992 Through 11-06-1992",

year = "1992",

doi = "10.1109/IJCNN.1992.227289",

language = "English (US)",

series = "Proceedings of the International Joint Conference on Neural Networks",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "55--60",

booktitle = "Proceedings - 1992 International Joint Conference on Neural Networks, IJCNN 1992",

}

TY - GEN

T1 - Biologically-Based Neural Network Model of Color Constancy and Color Contrast

AU - Courtney, Susan M.

AU - Buchsbaum, Gershon

AU - Finkel, Leif H.

N1 - Funding Information: Supported by grants from the McDonnell-Pew Program in Cognitive Neuroscience, the Whitaker Foundation, AFOSR 91-0082, and ONR N 00014-90-J-1864. Publisher Copyright: © 1992 IEEE.

PY - 1992

Y1 - 1992

N2 - The light which reaches the eye, or any other sensor, is the product of the reflectance and the illuminant Therefore, in order to determine the surface reflectance of an object independent of the illuminant, a system must use the spatiochromatic context of the image. We have developed a neural network based on the anatomy and physiology of the visual projection from retina to V4. The network combines color-opponent and contrast information to achieve a good degree of color constancy. This network has been tested on simulated images corresponding to the stimuli used in well established psychophysical experiments. Responses qualitatively match human responses to a variety of centersurround and Mondrian test stimuli.

AB - The light which reaches the eye, or any other sensor, is the product of the reflectance and the illuminant Therefore, in order to determine the surface reflectance of an object independent of the illuminant, a system must use the spatiochromatic context of the image. We have developed a neural network based on the anatomy and physiology of the visual projection from retina to V4. The network combines color-opponent and contrast information to achieve a good degree of color constancy. This network has been tested on simulated images corresponding to the stimuli used in well established psychophysical experiments. Responses qualitatively match human responses to a variety of centersurround and Mondrian test stimuli.

UR - https://www.scopus.com/pages/publications/84965529291

UR - https://www.scopus.com/pages/publications/84965529291#tab=citedBy

U2 - 10.1109/IJCNN.1992.227289

DO - 10.1109/IJCNN.1992.227289

M3 - Conference contribution

AN - SCOPUS:84965529291

T3 - Proceedings of the International Joint Conference on Neural Networks

SP - 55

EP - 60

BT - Proceedings - 1992 International Joint Conference on Neural Networks, IJCNN 1992

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 1992 International Joint Conference on Neural Networks, IJCNN 1992

Y2 - 7 June 1992 through 11 June 1992

ER -

Biologically-Based Neural Network Model of Color Constancy and Color Contrast

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this