Gabor-Feature Hallucination based on Generalized Canonical Correlation Analysis for face recognition

Kuong Hon Pong; Kin Man Lam

doi:10.1109/ISPACS.2011.6146163

Gabor-Feature Hallucination based on Generalized Canonical Correlation Analysis for face recognition

Kuong Hon Pong
, Kin Man Lam

The Hong Kong Polytechnic University

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

3 Citations (Scopus)

Abstract

In face recognition, image resolution is an important factor which has a great influence on the recognition rate. In traditional face recognition for low-resolution images, face interpolation/super-resolution is usually performed first, and the constructed high-resolution face image will then pass through a face recognition system, which includes feature extraction and classification. To achieve a more efficient and accurate approach, we propose a new method of Gabor-Feature Hallucination, which predicts the high-resolution Gabor features from the low-resolution Gabor features directly by using linear regression and Generalized Canonical Correlation Analysis. Then, the low-resolution features in the projected Generalized Canonical Correlation space and the predicted high-resolution Gabor features are adopted for face classification. Our algorithm can therefore avoid performing interpolation/super-resolution and high-resolution Gabor feature extraction. Experimental results show that the proposed method has a superior recognition rate and efficiency to the traditional methods.

Original language	English
Title of host publication	2011 International Symposium on Intelligent Signal Processing and Communications Systems
Subtitle of host publication	"The Decade of Intelligent and Green Signal Processing and Communications", ISPACS 2011
DOIs	https://doi.org/10.1109/ISPACS.2011.6146163
Publication status	Published - 1 Dec 2011
Event	19th IEEE International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2011 - Chiang Mai, Thailand Duration: 7 Dec 2011 → 9 Dec 2011

Conference

Conference	19th IEEE International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2011
Country/Territory	Thailand
City	Chiang Mai
Period	7/12/11 → 9/12/11

Keywords

face recognition
Gabor feature
generalized canonical correlation analysis
hallucination
linear regression

ASJC Scopus subject areas

Computer Networks and Communications
Signal Processing

More information

10.1109/ISPACS.2011.6146163

Cite this

Pong, K. H., & Lam, K. M. (2011). Gabor-Feature Hallucination based on Generalized Canonical Correlation Analysis for face recognition. In 2011 International Symposium on Intelligent Signal Processing and Communications Systems: "The Decade of Intelligent and Green Signal Processing and Communications", ISPACS 2011 Article 6146163 https://doi.org/10.1109/ISPACS.2011.6146163

@inproceedings{957757d924b643c8af43eb136f235c2c,

title = "Gabor-Feature Hallucination based on Generalized Canonical Correlation Analysis for face recognition",

abstract = "In face recognition, image resolution is an important factor which has a great influence on the recognition rate. In traditional face recognition for low-resolution images, face interpolation/super-resolution is usually performed first, and the constructed high-resolution face image will then pass through a face recognition system, which includes feature extraction and classification. To achieve a more efficient and accurate approach, we propose a new method of Gabor-Feature Hallucination, which predicts the high-resolution Gabor features from the low-resolution Gabor features directly by using linear regression and Generalized Canonical Correlation Analysis. Then, the low-resolution features in the projected Generalized Canonical Correlation space and the predicted high-resolution Gabor features are adopted for face classification. Our algorithm can therefore avoid performing interpolation/super-resolution and high-resolution Gabor feature extraction. Experimental results show that the proposed method has a superior recognition rate and efficiency to the traditional methods.",

keywords = "face recognition, Gabor feature, generalized canonical correlation analysis, hallucination, linear regression",

author = "Pong, \{Kuong Hon\} and Lam, \{Kin Man\}",

year = "2011",

month = dec,

day = "1",

doi = "10.1109/ISPACS.2011.6146163",

language = "English",

isbn = "9781457721663",

booktitle = "2011 International Symposium on Intelligent Signal Processing and Communications Systems",

note = "19th IEEE International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2011 ; Conference date: 07-12-2011 Through 09-12-2011",

}

Pong, KH & Lam, KM 2011, Gabor-Feature Hallucination based on Generalized Canonical Correlation Analysis for face recognition. in 2011 International Symposium on Intelligent Signal Processing and Communications Systems: "The Decade of Intelligent and Green Signal Processing and Communications", ISPACS 2011., 6146163, 19th IEEE International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2011, Chiang Mai, Thailand, 7/12/11. https://doi.org/10.1109/ISPACS.2011.6146163

Gabor-Feature Hallucination based on Generalized Canonical Correlation Analysis for face recognition. / Pong, Kuong Hon; Lam, Kin Man.
2011 International Symposium on Intelligent Signal Processing and Communications Systems: "The Decade of Intelligent and Green Signal Processing and Communications", ISPACS 2011. 2011. 6146163.

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

TY - GEN

T1 - Gabor-Feature Hallucination based on Generalized Canonical Correlation Analysis for face recognition

AU - Pong, Kuong Hon

AU - Lam, Kin Man

PY - 2011/12/1

Y1 - 2011/12/1

N2 - In face recognition, image resolution is an important factor which has a great influence on the recognition rate. In traditional face recognition for low-resolution images, face interpolation/super-resolution is usually performed first, and the constructed high-resolution face image will then pass through a face recognition system, which includes feature extraction and classification. To achieve a more efficient and accurate approach, we propose a new method of Gabor-Feature Hallucination, which predicts the high-resolution Gabor features from the low-resolution Gabor features directly by using linear regression and Generalized Canonical Correlation Analysis. Then, the low-resolution features in the projected Generalized Canonical Correlation space and the predicted high-resolution Gabor features are adopted for face classification. Our algorithm can therefore avoid performing interpolation/super-resolution and high-resolution Gabor feature extraction. Experimental results show that the proposed method has a superior recognition rate and efficiency to the traditional methods.

AB - In face recognition, image resolution is an important factor which has a great influence on the recognition rate. In traditional face recognition for low-resolution images, face interpolation/super-resolution is usually performed first, and the constructed high-resolution face image will then pass through a face recognition system, which includes feature extraction and classification. To achieve a more efficient and accurate approach, we propose a new method of Gabor-Feature Hallucination, which predicts the high-resolution Gabor features from the low-resolution Gabor features directly by using linear regression and Generalized Canonical Correlation Analysis. Then, the low-resolution features in the projected Generalized Canonical Correlation space and the predicted high-resolution Gabor features are adopted for face classification. Our algorithm can therefore avoid performing interpolation/super-resolution and high-resolution Gabor feature extraction. Experimental results show that the proposed method has a superior recognition rate and efficiency to the traditional methods.

KW - face recognition

KW - Gabor feature

KW - generalized canonical correlation analysis

KW - hallucination

KW - linear regression

UR - https://www.scopus.com/pages/publications/84857303366

U2 - 10.1109/ISPACS.2011.6146163

DO - 10.1109/ISPACS.2011.6146163

M3 - Conference article published in proceeding or book

SN - 9781457721663

BT - 2011 International Symposium on Intelligent Signal Processing and Communications Systems

T2 - 19th IEEE International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2011

Y2 - 7 December 2011 through 9 December 2011

ER -

Gabor-Feature Hallucination based on Generalized Canonical Correlation Analysis for face recognition

Abstract

Conference

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this