A face and speech biometric verification system using a simple Bayesian structure

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

Identity verification systems that use a mono modal biometric always have to contend with sensor noise and limitations of the feature extractor and matcher, while combining information from different biometrics modalities may well provide higher and more consistent performance levels. However, an intelligent scheme is required to fuse the decisions produced by the individual sensors. This paper presents a decision fusion technique for a bimodal biometric verification system that makes use of facial and speech biometrics. The decision fusion schemes considered have simple Bayesian structures (SBS) that particularize the univariat Gaussian density function, Beta density function or Parzen window density estimation. SBS has advantages in terms of computation speed, storage space and its open framework. The performances of SBS is evaluated and compared with that of other classical classification approaches, such as sum rule and Multilayer Perceptron, on a bimodal database.

Original languageEnglish
Pages (from-to)1121-1137
Number of pages17
JournalJournal of Information Science and Engineering
Volume21
Issue number6
Publication statusPublished - Nov 2005

Fingerprint

Biometrics
Probability density function
Fusion reactions
Sensors
Electric fuses
Multilayer neural networks
performance
decision making
biometrics

Keywords

  • Bimodal biometrics
  • Decision fusion
  • Face module
  • Simple bayesian structure
  • Speech module

ASJC Scopus subject areas

  • Information Systems

Cite this

A face and speech biometric verification system using a simple Bayesian structure. / Teoh, Andrew B J; Abdul Samad, Salina; Hussain, Aini.

In: Journal of Information Science and Engineering, Vol. 21, No. 6, 11.2005, p. 1121-1137.

Research output: Contribution to journalArticle

@article{1c0d8b91a8bf45ecbbea3d861029aa4c,
title = "A face and speech biometric verification system using a simple Bayesian structure",
abstract = "Identity verification systems that use a mono modal biometric always have to contend with sensor noise and limitations of the feature extractor and matcher, while combining information from different biometrics modalities may well provide higher and more consistent performance levels. However, an intelligent scheme is required to fuse the decisions produced by the individual sensors. This paper presents a decision fusion technique for a bimodal biometric verification system that makes use of facial and speech biometrics. The decision fusion schemes considered have simple Bayesian structures (SBS) that particularize the univariat Gaussian density function, Beta density function or Parzen window density estimation. SBS has advantages in terms of computation speed, storage space and its open framework. The performances of SBS is evaluated and compared with that of other classical classification approaches, such as sum rule and Multilayer Perceptron, on a bimodal database.",
keywords = "Bimodal biometrics, Decision fusion, Face module, Simple bayesian structure, Speech module",
author = "Teoh, {Andrew B J} and {Abdul Samad}, Salina and Aini Hussain",
year = "2005",
month = "11",
language = "English",
volume = "21",
pages = "1121--1137",
journal = "Journal of Information Science and Engineering",
issn = "1016-2364",
publisher = "Institute of Information Science",
number = "6",

}

TY - JOUR

T1 - A face and speech biometric verification system using a simple Bayesian structure

AU - Teoh, Andrew B J

AU - Abdul Samad, Salina

AU - Hussain, Aini

PY - 2005/11

Y1 - 2005/11

N2 - Identity verification systems that use a mono modal biometric always have to contend with sensor noise and limitations of the feature extractor and matcher, while combining information from different biometrics modalities may well provide higher and more consistent performance levels. However, an intelligent scheme is required to fuse the decisions produced by the individual sensors. This paper presents a decision fusion technique for a bimodal biometric verification system that makes use of facial and speech biometrics. The decision fusion schemes considered have simple Bayesian structures (SBS) that particularize the univariat Gaussian density function, Beta density function or Parzen window density estimation. SBS has advantages in terms of computation speed, storage space and its open framework. The performances of SBS is evaluated and compared with that of other classical classification approaches, such as sum rule and Multilayer Perceptron, on a bimodal database.

AB - Identity verification systems that use a mono modal biometric always have to contend with sensor noise and limitations of the feature extractor and matcher, while combining information from different biometrics modalities may well provide higher and more consistent performance levels. However, an intelligent scheme is required to fuse the decisions produced by the individual sensors. This paper presents a decision fusion technique for a bimodal biometric verification system that makes use of facial and speech biometrics. The decision fusion schemes considered have simple Bayesian structures (SBS) that particularize the univariat Gaussian density function, Beta density function or Parzen window density estimation. SBS has advantages in terms of computation speed, storage space and its open framework. The performances of SBS is evaluated and compared with that of other classical classification approaches, such as sum rule and Multilayer Perceptron, on a bimodal database.

KW - Bimodal biometrics

KW - Decision fusion

KW - Face module

KW - Simple bayesian structure

KW - Speech module

UR - http://www.scopus.com/inward/record.url?scp=28444474576&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=28444474576&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:28444474576

VL - 21

SP - 1121

EP - 1137

JO - Journal of Information Science and Engineering

JF - Journal of Information Science and Engineering

SN - 1016-2364

IS - 6

ER -