Nearest-subspace patch matching for face recognition under varying pose and illumination

Zihan Zhou, Arvind Ganesh, John Wright, Shen Fu Tsai, Yi Ma

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

14 Citations (Scopus)

Abstract

We consider the problem of recognizing human faces despite variations in both pose and illumination, using only frontal training images. We propose a very simple algorithm, called Nearest-Subspace Patch Matching, which combines a local translational model for deformation due to pose with a linear subspace model for lighting variations. This algorithm gives surprisingly competitive performance for moderate variations in both pose and illumination, a domain that encompasses most face recognition applications, such as access control. The results also provide a baseline for justifying the use of more complicated face models or more advanced learning methods to handle more extreme situations. Extensive experiments on publicly available databases verify the efficacy of the proposed method and clarify its operating range.

Original languageEnglish (US)
Title of host publication2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008
DOIs
StatePublished - Dec 1 2008
Event2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008 - Amsterdam, Netherlands
Duration: Sep 17 2008Sep 19 2008

Publication series

Name2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008

Conference

Conference2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008
CountryNetherlands
CityAmsterdam
Period9/17/089/19/08

Fingerprint

Face recognition
Lighting
Access control
Experiments

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition
  • Human-Computer Interaction
  • Electrical and Electronic Engineering

Cite this

Zhou, Z., Ganesh, A., Wright, J., Tsai, S. F., & Ma, Y. (2008). Nearest-subspace patch matching for face recognition under varying pose and illumination. In 2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008 [4813452] (2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008). https://doi.org/10.1109/AFGR.2008.4813452
Zhou, Zihan ; Ganesh, Arvind ; Wright, John ; Tsai, Shen Fu ; Ma, Yi. / Nearest-subspace patch matching for face recognition under varying pose and illumination. 2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008. 2008. (2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008).
@inproceedings{54d57a52add445f5b358a14add90f769,
title = "Nearest-subspace patch matching for face recognition under varying pose and illumination",
abstract = "We consider the problem of recognizing human faces despite variations in both pose and illumination, using only frontal training images. We propose a very simple algorithm, called Nearest-Subspace Patch Matching, which combines a local translational model for deformation due to pose with a linear subspace model for lighting variations. This algorithm gives surprisingly competitive performance for moderate variations in both pose and illumination, a domain that encompasses most face recognition applications, such as access control. The results also provide a baseline for justifying the use of more complicated face models or more advanced learning methods to handle more extreme situations. Extensive experiments on publicly available databases verify the efficacy of the proposed method and clarify its operating range.",
author = "Zihan Zhou and Arvind Ganesh and John Wright and Tsai, {Shen Fu} and Yi Ma",
year = "2008",
month = "12",
day = "1",
doi = "10.1109/AFGR.2008.4813452",
language = "English (US)",
isbn = "9781424421541",
series = "2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008",
booktitle = "2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008",

}

Zhou, Z, Ganesh, A, Wright, J, Tsai, SF & Ma, Y 2008, Nearest-subspace patch matching for face recognition under varying pose and illumination. in 2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008., 4813452, 2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008, 2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008, Amsterdam, Netherlands, 9/17/08. https://doi.org/10.1109/AFGR.2008.4813452

Nearest-subspace patch matching for face recognition under varying pose and illumination. / Zhou, Zihan; Ganesh, Arvind; Wright, John; Tsai, Shen Fu; Ma, Yi.

2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008. 2008. 4813452 (2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008).

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

TY - GEN

T1 - Nearest-subspace patch matching for face recognition under varying pose and illumination

AU - Zhou, Zihan

AU - Ganesh, Arvind

AU - Wright, John

AU - Tsai, Shen Fu

AU - Ma, Yi

PY - 2008/12/1

Y1 - 2008/12/1

N2 - We consider the problem of recognizing human faces despite variations in both pose and illumination, using only frontal training images. We propose a very simple algorithm, called Nearest-Subspace Patch Matching, which combines a local translational model for deformation due to pose with a linear subspace model for lighting variations. This algorithm gives surprisingly competitive performance for moderate variations in both pose and illumination, a domain that encompasses most face recognition applications, such as access control. The results also provide a baseline for justifying the use of more complicated face models or more advanced learning methods to handle more extreme situations. Extensive experiments on publicly available databases verify the efficacy of the proposed method and clarify its operating range.

AB - We consider the problem of recognizing human faces despite variations in both pose and illumination, using only frontal training images. We propose a very simple algorithm, called Nearest-Subspace Patch Matching, which combines a local translational model for deformation due to pose with a linear subspace model for lighting variations. This algorithm gives surprisingly competitive performance for moderate variations in both pose and illumination, a domain that encompasses most face recognition applications, such as access control. The results also provide a baseline for justifying the use of more complicated face models or more advanced learning methods to handle more extreme situations. Extensive experiments on publicly available databases verify the efficacy of the proposed method and clarify its operating range.

UR - http://www.scopus.com/inward/record.url?scp=67650688562&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67650688562&partnerID=8YFLogxK

U2 - 10.1109/AFGR.2008.4813452

DO - 10.1109/AFGR.2008.4813452

M3 - Conference contribution

AN - SCOPUS:67650688562

SN - 9781424421541

T3 - 2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008

BT - 2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008

ER -

Zhou Z, Ganesh A, Wright J, Tsai SF, Ma Y. Nearest-subspace patch matching for face recognition under varying pose and illumination. In 2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008. 2008. 4813452. (2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008). https://doi.org/10.1109/AFGR.2008.4813452