Exploiting global and local decisions for multimodal biometrics verification

Kar Ann Toh, Xudong Jiang, Wei Yun Yau

Research output: Contribution to journalArticle

77 Citations (Scopus)

Abstract

In this paper, we address the multimodal biometric decision fusion problem. By exploring into the user-specific approach for learning and threshold setting, four possible paradigms for learning and decision making are investigated. Since each user requires a decision hyperplane specific to him in order to achieve good verification accuracy, those tedious iterative training methods like the neural network approach would not be suitable. We propose to use a model that requires only a single training step for this application. The four global and local learning and decision paradigms are then explored to observe their decision capability. Besides the proposal of a relevant receiver operating characteristic performance for the local decision, extensive experiments were conducted to observe the verification performance for fusion of two and three biometrics.

Original languageEnglish
Pages (from-to)3059-3072
Number of pages14
JournalIEEE Transactions on Signal Processing
Volume52
Issue number10
DOIs
Publication statusPublished - 2004 Oct 1

Fingerprint

Biometrics
Fusion reactions
Decision making
Neural networks
Experiments

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

@article{0ebe9ed7c1b54ed89732d8dceaee03f7,
title = "Exploiting global and local decisions for multimodal biometrics verification",
abstract = "In this paper, we address the multimodal biometric decision fusion problem. By exploring into the user-specific approach for learning and threshold setting, four possible paradigms for learning and decision making are investigated. Since each user requires a decision hyperplane specific to him in order to achieve good verification accuracy, those tedious iterative training methods like the neural network approach would not be suitable. We propose to use a model that requires only a single training step for this application. The four global and local learning and decision paradigms are then explored to observe their decision capability. Besides the proposal of a relevant receiver operating characteristic performance for the local decision, extensive experiments were conducted to observe the verification performance for fusion of two and three biometrics.",
author = "Toh, {Kar Ann} and Xudong Jiang and Yau, {Wei Yun}",
year = "2004",
month = "10",
day = "1",
doi = "10.1109/TSP.2004.833862",
language = "English",
volume = "52",
pages = "3059--3072",
journal = "IEEE Transactions on Signal Processing",
issn = "1053-587X",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "10",

}

Exploiting global and local decisions for multimodal biometrics verification. / Toh, Kar Ann; Jiang, Xudong; Yau, Wei Yun.

In: IEEE Transactions on Signal Processing, Vol. 52, No. 10, 01.10.2004, p. 3059-3072.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Exploiting global and local decisions for multimodal biometrics verification

AU - Toh, Kar Ann

AU - Jiang, Xudong

AU - Yau, Wei Yun

PY - 2004/10/1

Y1 - 2004/10/1

N2 - In this paper, we address the multimodal biometric decision fusion problem. By exploring into the user-specific approach for learning and threshold setting, four possible paradigms for learning and decision making are investigated. Since each user requires a decision hyperplane specific to him in order to achieve good verification accuracy, those tedious iterative training methods like the neural network approach would not be suitable. We propose to use a model that requires only a single training step for this application. The four global and local learning and decision paradigms are then explored to observe their decision capability. Besides the proposal of a relevant receiver operating characteristic performance for the local decision, extensive experiments were conducted to observe the verification performance for fusion of two and three biometrics.

AB - In this paper, we address the multimodal biometric decision fusion problem. By exploring into the user-specific approach for learning and threshold setting, four possible paradigms for learning and decision making are investigated. Since each user requires a decision hyperplane specific to him in order to achieve good verification accuracy, those tedious iterative training methods like the neural network approach would not be suitable. We propose to use a model that requires only a single training step for this application. The four global and local learning and decision paradigms are then explored to observe their decision capability. Besides the proposal of a relevant receiver operating characteristic performance for the local decision, extensive experiments were conducted to observe the verification performance for fusion of two and three biometrics.

UR - http://www.scopus.com/inward/record.url?scp=4744361171&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=4744361171&partnerID=8YFLogxK

U2 - 10.1109/TSP.2004.833862

DO - 10.1109/TSP.2004.833862

M3 - Article

VL - 52

SP - 3059

EP - 3072

JO - IEEE Transactions on Signal Processing

JF - IEEE Transactions on Signal Processing

SN - 1053-587X

IS - 10

ER -