Appearance-based face recognition using aggregated 2D Gabor features

King Hong Cheung; Jia You; Qin Li; Prabir Bhattacharya

Appearance-based face recognition using aggregated 2D Gabor features

King Hong Cheung, Jia You, Qin Li, Prabir Bhattacharya

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › 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
Title of host publication	Proceedings of the 5th International Workshop on Pattern Recognition in Information Systems, PRIS 2005, in Conjunction with ICEIS 2005
Pages	3-11
Number of pages	9
Publication status	Published - 1 Dec 2005
Event	5th International Workshop on Pattern Recognition in Information Systems, PRIS 2005, in Conjunction with ICEIS 2005 - Miami, FL, United States Duration: 24 May 2005 → 25 May 2005

Conference

Conference	5th International Workshop on Pattern Recognition in Information Systems, PRIS 2005, in Conjunction with ICEIS 2005
Country/Territory	United States
City	Miami, FL
Period	24/05/05 → 25/05/05

ASJC Scopus subject areas

Computer Vision and Pattern Recognition
Information Systems

Cite this

@inproceedings{8a363af1404f4f198c860d39ca17b9bc,

title = "Appearance-based face recognition using aggregated 2D Gabor features",

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.",

author = "Cheung, {King Hong} and Jia You and Qin Li and Prabir Bhattacharya",

year = "2005",

month = dec,

day = "1",

language = "English",

isbn = "9728865287",

pages = "3--11",

booktitle = "Proceedings of the 5th International Workshop on Pattern Recognition in Information Systems, PRIS 2005, in Conjunction with ICEIS 2005",

note = "5th International Workshop on Pattern Recognition in Information Systems, PRIS 2005, in Conjunction with ICEIS 2005 ; Conference date: 24-05-2005 Through 25-05-2005",

}

Cheung, KH, You, J, Li, Q & Bhattacharya, P 2005, Appearance-based face recognition using aggregated 2D Gabor features. in Proceedings of the 5th International Workshop on Pattern Recognition in Information Systems, PRIS 2005, in Conjunction with ICEIS 2005. pp. 3-11, 5th International Workshop on Pattern Recognition in Information Systems, PRIS 2005, in Conjunction with ICEIS 2005, Miami, FL, United States, 24/05/05.

Appearance-based face recognition using aggregated 2D Gabor features. / Cheung, King Hong; You, Jia; Li, Qin et al.
Proceedings of the 5th International Workshop on Pattern Recognition in Information Systems, PRIS 2005, in Conjunction with ICEIS 2005. 2005. p. 3-11.

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - Appearance-based face recognition using aggregated 2D Gabor features

AU - Cheung, King Hong

AU - You, Jia

AU - Li, Qin

AU - Bhattacharya, Prabir

PY - 2005/12/1

Y1 - 2005/12/1

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.

UR - http://www.scopus.com/inward/record.url?scp=78651442156&partnerID=8YFLogxK

M3 - Conference article published in proceeding or book

SN - 9728865287

SN - 9789728865283

SP - 3

EP - 11

BT - Proceedings of the 5th International Workshop on Pattern Recognition in Information Systems, PRIS 2005, in Conjunction with ICEIS 2005

T2 - 5th International Workshop on Pattern Recognition in Information Systems, PRIS 2005, in Conjunction with ICEIS 2005

Y2 - 24 May 2005 through 25 May 2005

ER -

Appearance-based face recognition using aggregated 2D Gabor features

Abstract

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this