Optimal decision fusion for a face verification system

Q. Tao; Raymond N.J. Veldhuis

doi:10.1007/978-3-540-74549-5_100

Optimal decision fusion for a face verification system

Q. Tao, Raymond N.J. Veldhuis

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

7 Citations (Scopus)

120 Downloads (Pure)

Abstract

Fusion is a popular practice to increase the reliability of the biometric verification. In this paper, optimal fusion at decision level by AND rule and OR rule is investigated. Both a theoretical analysis and the experimental results are given. Comparisons are presented between fusion at decision level and fusion at matching score level. For our face verification system, decision fusion proves to be a simple, practical, and effective approach, which significantly improves the performance of the original classifier.

Original language	English
Title of host publication	Proceedings of the 2nd International Conference on Biometrics
Editors	L. Seong-Whan, Z.L. Stan
Place of Publication	Berlin Heidelberg
Publisher	Springer
Pages	958-967
Number of pages	10
ISBN (Print)	978-3-540-74548-8
DOIs	https://doi.org/10.1007/978-3-540-74549-5_100
Publication status	Published - 27 Aug 2007
Event	2nd International Conference on Biometrics, ICB 2007 - Seoul, Korea, Republic of Duration: 27 Aug 2007 → 29 Aug 2007 Conference number: 2

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer Verlag
Number	LNCS4549
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	2nd International Conference on Biometrics, ICB 2007
Abbreviated title	ICB
Country/Territory	Korea, Republic of
City	Seoul
Period	27/08/07 → 29/08/07

Keywords

SCS-Safety
METIS-241889
EWI-11018
IR-64333

Access to Document

10.1007/978-3-540-74549-5_100

Cite this

@inproceedings{ba3f6b5dbcab49d6bb9cd9c89e573a4d,

title = "Optimal decision fusion for a face verification system",

abstract = "Fusion is a popular practice to increase the reliability of the biometric verification. In this paper, optimal fusion at decision level by AND rule and OR rule is investigated. Both a theoretical analysis and the experimental results are given. Comparisons are presented between fusion at decision level and fusion at matching score level. For our face verification system, decision fusion proves to be a simple, practical, and effective approach, which significantly improves the performance of the original classifier.",

keywords = "SCS-Safety, METIS-241889, EWI-11018, IR-64333",

author = "Q. Tao and Veldhuis, {Raymond N.J.}",

note = "SAS 28-07; 2nd International Conference on Biometrics, ICB 2007, ICB ; Conference date: 27-08-2007 Through 29-08-2007",

year = "2007",

month = aug,

day = "27",

doi = "10.1007/978-3-540-74549-5_100",

language = "English",

isbn = "978-3-540-74548-8",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

number = "LNCS4549",

pages = "958--967",

editor = "L. Seong-Whan and Z.L. Stan",

booktitle = "Proceedings of the 2nd International Conference on Biometrics",

address = "Germany",

}

Tao, Q & Veldhuis, RNJ 2007, Optimal decision fusion for a face verification system. in L Seong-Whan & ZL Stan (eds), Proceedings of the 2nd International Conference on Biometrics. Lecture Notes in Computer Science, no. LNCS4549, Springer, Berlin Heidelberg, pp. 958-967, 2nd International Conference on Biometrics, ICB 2007, Seoul, Korea, Republic of, 27/08/07. https://doi.org/10.1007/978-3-540-74549-5_100

Optimal decision fusion for a face verification system. / Tao, Q.; Veldhuis, Raymond N.J.
Proceedings of the 2nd International Conference on Biometrics. ed. / L. Seong-Whan; Z.L. Stan. Berlin Heidelberg: Springer, 2007. p. 958-967 (Lecture Notes in Computer Science; No. LNCS4549).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Optimal decision fusion for a face verification system

AU - Tao, Q.

AU - Veldhuis, Raymond N.J.

N1 - Conference code: 2

PY - 2007/8/27

Y1 - 2007/8/27

N2 - Fusion is a popular practice to increase the reliability of the biometric verification. In this paper, optimal fusion at decision level by AND rule and OR rule is investigated. Both a theoretical analysis and the experimental results are given. Comparisons are presented between fusion at decision level and fusion at matching score level. For our face verification system, decision fusion proves to be a simple, practical, and effective approach, which significantly improves the performance of the original classifier.

AB - Fusion is a popular practice to increase the reliability of the biometric verification. In this paper, optimal fusion at decision level by AND rule and OR rule is investigated. Both a theoretical analysis and the experimental results are given. Comparisons are presented between fusion at decision level and fusion at matching score level. For our face verification system, decision fusion proves to be a simple, practical, and effective approach, which significantly improves the performance of the original classifier.

KW - SCS-Safety

KW - METIS-241889

KW - EWI-11018

KW - IR-64333

U2 - 10.1007/978-3-540-74549-5_100

DO - 10.1007/978-3-540-74549-5_100

M3 - Conference contribution

SN - 978-3-540-74548-8

T3 - Lecture Notes in Computer Science

SP - 958

EP - 967

BT - Proceedings of the 2nd International Conference on Biometrics

A2 - Seong-Whan, L.

A2 - Stan, Z.L.

PB - Springer

CY - Berlin Heidelberg

T2 - 2nd International Conference on Biometrics, ICB 2007

Y2 - 27 August 2007 through 29 August 2007

ER -

Optimal decision fusion for a face verification system

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this