Novel approach to colour constancy

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

It is shown that color constancy can be achieved only under a restricted set of circumstances. An algorithm is discussed that utilizes only structure intrinsic to the problem of color constancy. This algorithm is robust and flexible, and can easily be learned by observing photoreceptor responses. In particular this approach generalizes naturally to the case when there is spatial variation in the illuminant content, and has been shown to work on real color images. This formulation is also shown to be capable of reproducing qualitative aspects of E. H. Land's two color experiments (1986).

Original languageEnglish (US)
Title of host publicationSecond Int Conf on Comput Vision
PublisherPubl by IEEE
Pages9-18
Number of pages10
ISBN (Print)0818608838
StatePublished - 1988
Externally publishedYes

Fingerprint

Color
Experiments

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Forsyth, D. A. (1988). Novel approach to colour constancy. In Second Int Conf on Comput Vision (pp. 9-18). Publ by IEEE.

Novel approach to colour constancy. / Forsyth, David Alexander.

Second Int Conf on Comput Vision. Publ by IEEE, 1988. p. 9-18.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Forsyth, DA 1988, Novel approach to colour constancy. in Second Int Conf on Comput Vision. Publ by IEEE, pp. 9-18.
Forsyth DA. Novel approach to colour constancy. In Second Int Conf on Comput Vision. Publ by IEEE. 1988. p. 9-18
Forsyth, David Alexander. / Novel approach to colour constancy. Second Int Conf on Comput Vision. Publ by IEEE, 1988. pp. 9-18
@inproceedings{a94cca922ff34a599cd66d9aef2a1142,
title = "Novel approach to colour constancy",
abstract = "It is shown that color constancy can be achieved only under a restricted set of circumstances. An algorithm is discussed that utilizes only structure intrinsic to the problem of color constancy. This algorithm is robust and flexible, and can easily be learned by observing photoreceptor responses. In particular this approach generalizes naturally to the case when there is spatial variation in the illuminant content, and has been shown to work on real color images. This formulation is also shown to be capable of reproducing qualitative aspects of E. H. Land's two color experiments (1986).",
author = "Forsyth, {David Alexander}",
year = "1988",
language = "English (US)",
isbn = "0818608838",
pages = "9--18",
booktitle = "Second Int Conf on Comput Vision",
publisher = "Publ by IEEE",

}

TY - GEN

T1 - Novel approach to colour constancy

AU - Forsyth, David Alexander

PY - 1988

Y1 - 1988

N2 - It is shown that color constancy can be achieved only under a restricted set of circumstances. An algorithm is discussed that utilizes only structure intrinsic to the problem of color constancy. This algorithm is robust and flexible, and can easily be learned by observing photoreceptor responses. In particular this approach generalizes naturally to the case when there is spatial variation in the illuminant content, and has been shown to work on real color images. This formulation is also shown to be capable of reproducing qualitative aspects of E. H. Land's two color experiments (1986).

AB - It is shown that color constancy can be achieved only under a restricted set of circumstances. An algorithm is discussed that utilizes only structure intrinsic to the problem of color constancy. This algorithm is robust and flexible, and can easily be learned by observing photoreceptor responses. In particular this approach generalizes naturally to the case when there is spatial variation in the illuminant content, and has been shown to work on real color images. This formulation is also shown to be capable of reproducing qualitative aspects of E. H. Land's two color experiments (1986).

UR - http://www.scopus.com/inward/record.url?scp=0024170470&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0024170470&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0024170470

SN - 0818608838

SP - 9

EP - 18

BT - Second Int Conf on Comput Vision

PB - Publ by IEEE

ER -