Face recognition by regularized discriminant analysis

Dao Qing Dai; Pong Chi YUEN

doi:10.1109/TSMCB.2007.895363

Face recognition by regularized discriminant analysis

Dao Qing Dai^*, Pong Chi YUEN

^*Corresponding author for this work

Department of Computer Science

Research output: Contribution to journal › Article › peer-review

71 Citations (Scopus)

Abstract

When the feature dimension is larger than the number of samples the small sample-size problem occurs. There is great concern about it within the face recognition community. We point out that optimizing the Fisher index in linear discriminant analysis does not necessarily give the best performance for a face recognition system. We propose a new regularization scheme. The proposed method is evaluated using the Olivetti Research Laboratory database, the Yale database, and the Feret database.

Original language	English
Pages (from-to)	1080-1085
Number of pages	6
Journal	IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Volume	37
Issue number	4
DOIs	https://doi.org/10.1109/TSMCB.2007.895363
Publication status	Published - Aug 2007

Scopus Subject Areas

Control and Systems Engineering
Software
Information Systems
Human-Computer Interaction
Computer Science Applications
Electrical and Electronic Engineering

User-Defined Keywords

Face recognition
Optimization
Regularized discriminant analysis (RDA)
Small sample-size problem

Access to Document

10.1109/TSMCB.2007.895363

Cite this

@article{957d8173f1ff427399951d36cfd81532,

title = "Face recognition by regularized discriminant analysis",

abstract = "When the feature dimension is larger than the number of samples the small sample-size problem occurs. There is great concern about it within the face recognition community. We point out that optimizing the Fisher index in linear discriminant analysis does not necessarily give the best performance for a face recognition system. We propose a new regularization scheme. The proposed method is evaluated using the Olivetti Research Laboratory database, the Yale database, and the Feret database.",

keywords = "Face recognition, Optimization, Regularized discriminant analysis (RDA), Small sample-size problem",

author = "Dai, {Dao Qing} and YUEN, {Pong Chi}",

note = "Funding Information: Manuscript received December 9, 2005; revised June 14, 2006. This work was supported in part by the National Science Foundation (NSF) of China under Grants 60175031, 60575004, and 10231040, by the NSF of GuangDong under Grant 05101817, by the Ministry of Education of China under Grant NCET-04-0791, and by the Research Grant Council (RGC) Earmarked Research Grant HKBU-2119/03E. This paper was recommended by Associate Editor N. K. Ratha.",

year = "2007",

month = aug,

doi = "10.1109/TSMCB.2007.895363",

language = "English",

volume = "37",

pages = "1080--1085",

journal = "IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics",

issn = "1083-4419",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "4",

}

TY - JOUR

T1 - Face recognition by regularized discriminant analysis

AU - Dai, Dao Qing

AU - YUEN, Pong Chi

N1 - Funding Information: Manuscript received December 9, 2005; revised June 14, 2006. This work was supported in part by the National Science Foundation (NSF) of China under Grants 60175031, 60575004, and 10231040, by the NSF of GuangDong under Grant 05101817, by the Ministry of Education of China under Grant NCET-04-0791, and by the Research Grant Council (RGC) Earmarked Research Grant HKBU-2119/03E. This paper was recommended by Associate Editor N. K. Ratha.

PY - 2007/8

Y1 - 2007/8

N2 - When the feature dimension is larger than the number of samples the small sample-size problem occurs. There is great concern about it within the face recognition community. We point out that optimizing the Fisher index in linear discriminant analysis does not necessarily give the best performance for a face recognition system. We propose a new regularization scheme. The proposed method is evaluated using the Olivetti Research Laboratory database, the Yale database, and the Feret database.

AB - When the feature dimension is larger than the number of samples the small sample-size problem occurs. There is great concern about it within the face recognition community. We point out that optimizing the Fisher index in linear discriminant analysis does not necessarily give the best performance for a face recognition system. We propose a new regularization scheme. The proposed method is evaluated using the Olivetti Research Laboratory database, the Yale database, and the Feret database.

KW - Face recognition

KW - Optimization

KW - Regularized discriminant analysis (RDA)

KW - Small sample-size problem

UR - http://www.scopus.com/inward/record.url?scp=34547112821&partnerID=8YFLogxK

U2 - 10.1109/TSMCB.2007.895363

DO - 10.1109/TSMCB.2007.895363

M3 - Article

C2 - 17702305

AN - SCOPUS:34547112821

VL - 37

SP - 1080

EP - 1085

JO - IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

JF - IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

SN - 1083-4419

IS - 4

ER -

Face recognition by regularized discriminant analysis

Abstract

Scopus Subject Areas

User-Defined Keywords

Access to Document

Other files and links

Fingerprint

Cite this