A new approach to appearance-based face recognition

K. H. Cheung; A. Kong; Jia You; Q. Li; Dapeng Zhang; Prabir Bhattacharya

A new approach to appearance-based face recognition

K. H. Cheung, A. Kong, Jia You, Q. Li, Dapeng Zhang, Prabir Bhattacharya

Research output: Journal article publication › Conference article › Academic research › peer-review

Abstract

Current holistic appearance based face recognition methods require a high dimensional feature space to attain fruitful performance. In this paper, we have proposed a relatively low feature dimensional, template-matching scheme to cope with the transformed appearance-based face recognition problem. We use aggregated Gabor filter responses to represent face images. We investigated the effect of "duplicate" images (images from different sessions) and the effect of facial expressions. Our results indicate that the proposed method is more robust in recognizing "duplicate" images with variations in facial expression than the Principal Component Analysis method.

Original language	English
Pages (from-to)	1686-1691
Number of pages	6
Journal	Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics
Volume	2
Publication status	Published - 30 Nov 2005
Event	IEEE Systems, Man and Cybernetics Society, Proceedings - 2005 International Conference on Systems, Man and Cybernetics - Waikoloa, HI, United States Duration: 10 Oct 2005 → 12 Oct 2005

Keywords

Biometrics
Gabor filter feature
Holistic face recognition
Low feature dimensional

ASJC Scopus subject areas

General Engineering

Cite this

@article{8db0115534e245bdabad916a21b83ef2,

title = "A new approach to appearance-based face recognition",

abstract = "Current holistic appearance based face recognition methods require a high dimensional feature space to attain fruitful performance. In this paper, we have proposed a relatively low feature dimensional, template-matching scheme to cope with the transformed appearance-based face recognition problem. We use aggregated Gabor filter responses to represent face images. We investigated the effect of {"}duplicate{"} images (images from different sessions) and the effect of facial expressions. Our results indicate that the proposed method is more robust in recognizing {"}duplicate{"} images with variations in facial expression than the Principal Component Analysis method.",

keywords = "Biometrics, Gabor filter feature, Holistic face recognition, Low feature dimensional",

author = "Cheung, \{K. H.\} and A. Kong and Jia You and Q. Li and Dapeng Zhang and Prabir Bhattacharya",

year = "2005",

month = nov,

day = "30",

language = "English",

volume = "2",

pages = "1686--1691",

journal = "Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics",

issn = "1062-922X",

publisher = "IEEE",

note = "IEEE Systems, Man and Cybernetics Society, Proceedings - 2005 International Conference on Systems, Man and Cybernetics ; Conference date: 10-10-2005 Through 12-10-2005",

}

TY - JOUR

T1 - A new approach to appearance-based face recognition

AU - Cheung, K. H.

AU - Kong, A.

AU - You, Jia

AU - Li, Q.

AU - Zhang, Dapeng

AU - Bhattacharya, Prabir

PY - 2005/11/30

Y1 - 2005/11/30

N2 - Current holistic appearance based face recognition methods require a high dimensional feature space to attain fruitful performance. In this paper, we have proposed a relatively low feature dimensional, template-matching scheme to cope with the transformed appearance-based face recognition problem. We use aggregated Gabor filter responses to represent face images. We investigated the effect of "duplicate" images (images from different sessions) and the effect of facial expressions. Our results indicate that the proposed method is more robust in recognizing "duplicate" images with variations in facial expression than the Principal Component Analysis method.

AB - Current holistic appearance based face recognition methods require a high dimensional feature space to attain fruitful performance. In this paper, we have proposed a relatively low feature dimensional, template-matching scheme to cope with the transformed appearance-based face recognition problem. We use aggregated Gabor filter responses to represent face images. We investigated the effect of "duplicate" images (images from different sessions) and the effect of facial expressions. Our results indicate that the proposed method is more robust in recognizing "duplicate" images with variations in facial expression than the Principal Component Analysis method.

KW - Biometrics

KW - Gabor filter feature

KW - Holistic face recognition

KW - Low feature dimensional

UR - http://www.scopus.com/inward/record.url?scp=27944507280&partnerID=8YFLogxK

M3 - Conference article

SN - 1062-922X

VL - 2

SP - 1686

EP - 1691

JO - Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics

JF - Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics

T2 - IEEE Systems, Man and Cybernetics Society, Proceedings - 2005 International Conference on Systems, Man and Cybernetics

Y2 - 10 October 2005 through 12 October 2005

ER -

A new approach to appearance-based face recognition

Abstract

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this