Two-class linear discriminant analysis for face recognition

Hazim Kemal Ekenel; Rainer Stiefelhagen

doi:10.1109/SIU.2007.4298761

Two-class linear discriminant analysis for face recognition

Hazim Kemal Ekenel, Rainer Stiefelhagen

Computer Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

In this paper, we present a novel face recognition system that uses two-class linear discriminant analysis for classification. In this approach a single M-class linear discriminant clussifier is divided into M two-class linear discriminant classifiers. This formulation provides many advantages like more discrimination between classes, simpler calculation of projection vectors and easier update of the database with new individuals. We tested the proposed algorithm on the CMU PIE and Yale face databases. Significant performance improvements are observed, especially when the number of individuals to be classified increases.

Original language	English (US)
Title of host publication	2007 IEEE 15th Signal Processing and Communications Applications, SIU
DOIs	https://doi.org/10.1109/SIU.2007.4298761
State	Published - 2007
Event	2007 IEEE 15th Signal Processing and Communications Applications, SIU - Eskisehir, Turkey Duration: Jun 11 2007 → Jun 13 2007

Publication series

Name	2007 IEEE 15th Signal Processing and Communications Applications, SIU

Conference

Conference	2007 IEEE 15th Signal Processing and Communications Applications, SIU
Country/Territory	Turkey
City	Eskisehir
Period	6/11/07 → 6/13/07

ASJC Scopus subject areas

Computer Networks and Communications
Communication
Signal Processing

Access to Document

10.1109/SIU.2007.4298761

Cite this

Ekenel, HK & Stiefelhagen, R 2007, Two-class linear discriminant analysis for face recognition. in 2007 IEEE 15th Signal Processing and Communications Applications, SIU., 4298761, 2007 IEEE 15th Signal Processing and Communications Applications, SIU, 2007 IEEE 15th Signal Processing and Communications Applications, SIU, Eskisehir, Turkey, 6/11/07. https://doi.org/10.1109/SIU.2007.4298761

@inproceedings{a82e2f307fc54d0b92b951bd80d67926,

title = "Two-class linear discriminant analysis for face recognition",

abstract = "In this paper, we present a novel face recognition system that uses two-class linear discriminant analysis for classification. In this approach a single M-class linear discriminant clussifier is divided into M two-class linear discriminant classifiers. This formulation provides many advantages like more discrimination between classes, simpler calculation of projection vectors and easier update of the database with new individuals. We tested the proposed algorithm on the CMU PIE and Yale face databases. Significant performance improvements are observed, especially when the number of individuals to be classified increases.",

author = "Ekenel, {Hazim Kemal} and Rainer Stiefelhagen",

year = "2007",

doi = "10.1109/SIU.2007.4298761",

language = "English (US)",

isbn = "1424407192",

series = "2007 IEEE 15th Signal Processing and Communications Applications, SIU",

booktitle = "2007 IEEE 15th Signal Processing and Communications Applications, SIU",

note = "2007 IEEE 15th Signal Processing and Communications Applications, SIU ; Conference date: 11-06-2007 Through 13-06-2007",

}

TY - GEN

T1 - Two-class linear discriminant analysis for face recognition

AU - Ekenel, Hazim Kemal

AU - Stiefelhagen, Rainer

PY - 2007

Y1 - 2007

N2 - In this paper, we present a novel face recognition system that uses two-class linear discriminant analysis for classification. In this approach a single M-class linear discriminant clussifier is divided into M two-class linear discriminant classifiers. This formulation provides many advantages like more discrimination between classes, simpler calculation of projection vectors and easier update of the database with new individuals. We tested the proposed algorithm on the CMU PIE and Yale face databases. Significant performance improvements are observed, especially when the number of individuals to be classified increases.

AB - In this paper, we present a novel face recognition system that uses two-class linear discriminant analysis for classification. In this approach a single M-class linear discriminant clussifier is divided into M two-class linear discriminant classifiers. This formulation provides many advantages like more discrimination between classes, simpler calculation of projection vectors and easier update of the database with new individuals. We tested the proposed algorithm on the CMU PIE and Yale face databases. Significant performance improvements are observed, especially when the number of individuals to be classified increases.

UR - http://www.scopus.com/inward/record.url?scp=50249142970&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=50249142970&partnerID=8YFLogxK

U2 - 10.1109/SIU.2007.4298761

DO - 10.1109/SIU.2007.4298761

M3 - Conference contribution

AN - SCOPUS:50249142970

SN - 1424407192

SN - 9781424407194

T3 - 2007 IEEE 15th Signal Processing and Communications Applications, SIU

BT - 2007 IEEE 15th Signal Processing and Communications Applications, SIU

T2 - 2007 IEEE 15th Signal Processing and Communications Applications, SIU

Y2 - 11 June 2007 through 13 June 2007

ER -

Two-class linear discriminant analysis for face recognition

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this