Adaptation to changes in multimodal biometric authentication

Quoc Long Tran, Kar Ann Toh, Dipti Srinivasan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

Multimodal biometric authentication is gaining more and more attention recently. In [1], a Reduced Multivariate Polynomial model has been used to combine the biometric classifiers with good performance. Although the model parameter can be solved very quickly, it may not be suitable in case when new registration is a frequent task. Moreover, due to wear and tear of sensors, the distribution of match scores can change with time and hence the performance of a fixed classifier may be affected. In this paper, we introduce an adaptive algorithm to track these changes. The new algorithm is demonstrated to address both the registration and match scores distribution changing problems using two biometrics.

Original languageEnglish
Title of host publication2004 IEEE Conference on Cybernetics and Intelligent Systems
Pages981-985
Number of pages5
Publication statusPublished - 2004 Dec 1
Event2004 IEEE Conference on Cybernetics and Intelligent Systems - , Singapore
Duration: 2004 Dec 12004 Dec 3

Publication series

Name2004 IEEE Conference on Cybernetics and Intelligent Systems

Other

Other2004 IEEE Conference on Cybernetics and Intelligent Systems
CountrySingapore
Period04/12/104/12/3

Fingerprint

Biometrics
Authentication
Classifiers
Adaptive algorithms
Wear of materials
Sensors

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

Tran, Q. L., Toh, K. A., & Srinivasan, D. (2004). Adaptation to changes in multimodal biometric authentication. In 2004 IEEE Conference on Cybernetics and Intelligent Systems (pp. 981-985). (2004 IEEE Conference on Cybernetics and Intelligent Systems).
Tran, Quoc Long ; Toh, Kar Ann ; Srinivasan, Dipti. / Adaptation to changes in multimodal biometric authentication. 2004 IEEE Conference on Cybernetics and Intelligent Systems. 2004. pp. 981-985 (2004 IEEE Conference on Cybernetics and Intelligent Systems).
@inproceedings{a1c9fffb89204dd08bbac592f90f847c,
title = "Adaptation to changes in multimodal biometric authentication",
abstract = "Multimodal biometric authentication is gaining more and more attention recently. In [1], a Reduced Multivariate Polynomial model has been used to combine the biometric classifiers with good performance. Although the model parameter can be solved very quickly, it may not be suitable in case when new registration is a frequent task. Moreover, due to wear and tear of sensors, the distribution of match scores can change with time and hence the performance of a fixed classifier may be affected. In this paper, we introduce an adaptive algorithm to track these changes. The new algorithm is demonstrated to address both the registration and match scores distribution changing problems using two biometrics.",
author = "Tran, {Quoc Long} and Toh, {Kar Ann} and Dipti Srinivasan",
year = "2004",
month = "12",
day = "1",
language = "English",
isbn = "0780386442",
series = "2004 IEEE Conference on Cybernetics and Intelligent Systems",
pages = "981--985",
booktitle = "2004 IEEE Conference on Cybernetics and Intelligent Systems",

}

Tran, QL, Toh, KA & Srinivasan, D 2004, Adaptation to changes in multimodal biometric authentication. in 2004 IEEE Conference on Cybernetics and Intelligent Systems. 2004 IEEE Conference on Cybernetics and Intelligent Systems, pp. 981-985, 2004 IEEE Conference on Cybernetics and Intelligent Systems, Singapore, 04/12/1.

Adaptation to changes in multimodal biometric authentication. / Tran, Quoc Long; Toh, Kar Ann; Srinivasan, Dipti.

2004 IEEE Conference on Cybernetics and Intelligent Systems. 2004. p. 981-985 (2004 IEEE Conference on Cybernetics and Intelligent Systems).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Adaptation to changes in multimodal biometric authentication

AU - Tran, Quoc Long

AU - Toh, Kar Ann

AU - Srinivasan, Dipti

PY - 2004/12/1

Y1 - 2004/12/1

N2 - Multimodal biometric authentication is gaining more and more attention recently. In [1], a Reduced Multivariate Polynomial model has been used to combine the biometric classifiers with good performance. Although the model parameter can be solved very quickly, it may not be suitable in case when new registration is a frequent task. Moreover, due to wear and tear of sensors, the distribution of match scores can change with time and hence the performance of a fixed classifier may be affected. In this paper, we introduce an adaptive algorithm to track these changes. The new algorithm is demonstrated to address both the registration and match scores distribution changing problems using two biometrics.

AB - Multimodal biometric authentication is gaining more and more attention recently. In [1], a Reduced Multivariate Polynomial model has been used to combine the biometric classifiers with good performance. Although the model parameter can be solved very quickly, it may not be suitable in case when new registration is a frequent task. Moreover, due to wear and tear of sensors, the distribution of match scores can change with time and hence the performance of a fixed classifier may be affected. In this paper, we introduce an adaptive algorithm to track these changes. The new algorithm is demonstrated to address both the registration and match scores distribution changing problems using two biometrics.

UR - http://www.scopus.com/inward/record.url?scp=11244346955&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=11244346955&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:11244346955

SN - 0780386442

SN - 9780780386440

T3 - 2004 IEEE Conference on Cybernetics and Intelligent Systems

SP - 981

EP - 985

BT - 2004 IEEE Conference on Cybernetics and Intelligent Systems

ER -

Tran QL, Toh KA, Srinivasan D. Adaptation to changes in multimodal biometric authentication. In 2004 IEEE Conference on Cybernetics and Intelligent Systems. 2004. p. 981-985. (2004 IEEE Conference on Cybernetics and Intelligent Systems).