Robust face recognition across lighting variations using synthesized exemplars

Sang Woong Lee, Song Hyang Moon, Seong Whan Lee

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

Abstract

In this paper, we propose a new face recognition method under arbitrary lighting conditions, given only a single registered image and training data under unknown illuminations. Our proposed method is based on the exemplars which are synthesized from photometric stereo images of training data and the linear combination of those exemplars are used to represent the new face. We make experiments for verifying our approach and compare it with two traditional approaches. As a result, higher recognition rates are reported in these experiments using the illumination subset of Max-Planck Institute Face Database.

Original languageEnglish
Title of host publicationLecture Notes in Computer Science
EditorsD.-S. Huang, X.-P. Zhang, G.-B. Huang
Pages213-222
Number of pages10
Volume3644
EditionPART I
Publication statusPublished - 2005
EventInternational Conference on Intelligent Computing, ICIC 2005 - Hefei, China
Duration: 2005 Aug 232005 Aug 26

Other

OtherInternational Conference on Intelligent Computing, ICIC 2005
CountryChina
CityHefei
Period05/8/2305/8/26

Fingerprint

Face recognition
Lighting
Experiments

ASJC Scopus subject areas

  • Computer Science (miscellaneous)

Cite this

Lee, S. W., Moon, S. H., & Lee, S. W. (2005). Robust face recognition across lighting variations using synthesized exemplars. In D-S. Huang, X-P. Zhang, & G-B. Huang (Eds.), Lecture Notes in Computer Science (PART I ed., Vol. 3644, pp. 213-222)

Robust face recognition across lighting variations using synthesized exemplars. / Lee, Sang Woong; Moon, Song Hyang; Lee, Seong Whan.

Lecture Notes in Computer Science. ed. / D.-S. Huang; X.-P. Zhang; G.-B. Huang. Vol. 3644 PART I. ed. 2005. p. 213-222.

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

Lee, SW, Moon, SH & Lee, SW 2005, Robust face recognition across lighting variations using synthesized exemplars. in D-S Huang, X-P Zhang & G-B Huang (eds), Lecture Notes in Computer Science. PART I edn, vol. 3644, pp. 213-222, International Conference on Intelligent Computing, ICIC 2005, Hefei, China, 05/8/23.
Lee SW, Moon SH, Lee SW. Robust face recognition across lighting variations using synthesized exemplars. In Huang D-S, Zhang X-P, Huang G-B, editors, Lecture Notes in Computer Science. PART I ed. Vol. 3644. 2005. p. 213-222
Lee, Sang Woong ; Moon, Song Hyang ; Lee, Seong Whan. / Robust face recognition across lighting variations using synthesized exemplars. Lecture Notes in Computer Science. editor / D.-S. Huang ; X.-P. Zhang ; G.-B. Huang. Vol. 3644 PART I. ed. 2005. pp. 213-222
@inproceedings{90458f5a647f48ce94e5b8beb99726c5,
title = "Robust face recognition across lighting variations using synthesized exemplars",
abstract = "In this paper, we propose a new face recognition method under arbitrary lighting conditions, given only a single registered image and training data under unknown illuminations. Our proposed method is based on the exemplars which are synthesized from photometric stereo images of training data and the linear combination of those exemplars are used to represent the new face. We make experiments for verifying our approach and compare it with two traditional approaches. As a result, higher recognition rates are reported in these experiments using the illumination subset of Max-Planck Institute Face Database.",
author = "Lee, {Sang Woong} and Moon, {Song Hyang} and Lee, {Seong Whan}",
year = "2005",
language = "English",
volume = "3644",
pages = "213--222",
editor = "D.-S. Huang and X.-P. Zhang and G.-B. Huang",
booktitle = "Lecture Notes in Computer Science",
edition = "PART I",

}

TY - GEN

T1 - Robust face recognition across lighting variations using synthesized exemplars

AU - Lee, Sang Woong

AU - Moon, Song Hyang

AU - Lee, Seong Whan

PY - 2005

Y1 - 2005

N2 - In this paper, we propose a new face recognition method under arbitrary lighting conditions, given only a single registered image and training data under unknown illuminations. Our proposed method is based on the exemplars which are synthesized from photometric stereo images of training data and the linear combination of those exemplars are used to represent the new face. We make experiments for verifying our approach and compare it with two traditional approaches. As a result, higher recognition rates are reported in these experiments using the illumination subset of Max-Planck Institute Face Database.

AB - In this paper, we propose a new face recognition method under arbitrary lighting conditions, given only a single registered image and training data under unknown illuminations. Our proposed method is based on the exemplars which are synthesized from photometric stereo images of training data and the linear combination of those exemplars are used to represent the new face. We make experiments for verifying our approach and compare it with two traditional approaches. As a result, higher recognition rates are reported in these experiments using the illumination subset of Max-Planck Institute Face Database.

UR - http://www.scopus.com/inward/record.url?scp=27144436811&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=27144436811&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:27144436811

VL - 3644

SP - 213

EP - 222

BT - Lecture Notes in Computer Science

A2 - Huang, D.-S.

A2 - Zhang, X.-P.

A2 - Huang, G.-B.

ER -