Remarks on BioHashing based cancelable biometrics in verification system

Beng Jin Teoh, Tee Connie

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

Biometric characteristics are immutable and hence their compromise is permanent. To address this problem, cancelable biometrics was introduced to denote biometric templates that can be canceled and replaced. BioHash is a form of cancelable biometrics which mixes a set of user-specific random numbers with the biometric features. The main drawback of BioHash is its great degradation in performance when the legitimate token is stolen and used by the imposter to claim as the legitimate user. In this paper, we employ a modified probabilistic neural network as the classifier to alleviate this problem. The experiments are tested on the FERET face data set with promising results.

Original languageEnglish
Pages (from-to)2461-2464
Number of pages4
JournalNeurocomputing
Volume69
Issue number16-18
DOIs
Publication statusPublished - 2006 Oct 1

Fingerprint

Biometrics
Classifiers
Datasets
Neural networks
Degradation
Experiments

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Cellular and Molecular Neuroscience

Cite this

Teoh, Beng Jin ; Connie, Tee. / Remarks on BioHashing based cancelable biometrics in verification system. In: Neurocomputing. 2006 ; Vol. 69, No. 16-18. pp. 2461-2464.
@article{cedc01b670c741289f5786f7dcf26819,
title = "Remarks on BioHashing based cancelable biometrics in verification system",
abstract = "Biometric characteristics are immutable and hence their compromise is permanent. To address this problem, cancelable biometrics was introduced to denote biometric templates that can be canceled and replaced. BioHash is a form of cancelable biometrics which mixes a set of user-specific random numbers with the biometric features. The main drawback of BioHash is its great degradation in performance when the legitimate token is stolen and used by the imposter to claim as the legitimate user. In this paper, we employ a modified probabilistic neural network as the classifier to alleviate this problem. The experiments are tested on the FERET face data set with promising results.",
author = "Teoh, {Beng Jin} and Tee Connie",
year = "2006",
month = "10",
day = "1",
doi = "10.1016/j.neucom.2006.01.024",
language = "English",
volume = "69",
pages = "2461--2464",
journal = "Neurocomputing",
issn = "0925-2312",
publisher = "Elsevier",
number = "16-18",

}

Remarks on BioHashing based cancelable biometrics in verification system. / Teoh, Beng Jin; Connie, Tee.

In: Neurocomputing, Vol. 69, No. 16-18, 01.10.2006, p. 2461-2464.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Remarks on BioHashing based cancelable biometrics in verification system

AU - Teoh, Beng Jin

AU - Connie, Tee

PY - 2006/10/1

Y1 - 2006/10/1

N2 - Biometric characteristics are immutable and hence their compromise is permanent. To address this problem, cancelable biometrics was introduced to denote biometric templates that can be canceled and replaced. BioHash is a form of cancelable biometrics which mixes a set of user-specific random numbers with the biometric features. The main drawback of BioHash is its great degradation in performance when the legitimate token is stolen and used by the imposter to claim as the legitimate user. In this paper, we employ a modified probabilistic neural network as the classifier to alleviate this problem. The experiments are tested on the FERET face data set with promising results.

AB - Biometric characteristics are immutable and hence their compromise is permanent. To address this problem, cancelable biometrics was introduced to denote biometric templates that can be canceled and replaced. BioHash is a form of cancelable biometrics which mixes a set of user-specific random numbers with the biometric features. The main drawback of BioHash is its great degradation in performance when the legitimate token is stolen and used by the imposter to claim as the legitimate user. In this paper, we employ a modified probabilistic neural network as the classifier to alleviate this problem. The experiments are tested on the FERET face data set with promising results.

UR - http://www.scopus.com/inward/record.url?scp=33748421224&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33748421224&partnerID=8YFLogxK

U2 - 10.1016/j.neucom.2006.01.024

DO - 10.1016/j.neucom.2006.01.024

M3 - Article

AN - SCOPUS:33748421224

VL - 69

SP - 2461

EP - 2464

JO - Neurocomputing

JF - Neurocomputing

SN - 0925-2312

IS - 16-18

ER -