Cancelable biometrics realization with multispace random projections

Andrew Beng Jin Teoh, Chong Tze Yuang

Research output: Contribution to journalArticle

95 Citations (Scopus)

Abstract

Biometric characteristics cannot be changed; therefore, the loss of privacy is permanent if they are ever compromised. This paper presents a two-factor cancelable formulation, where the biometric data are distorted in a revocable but nonreversible manner by first transforming the raw biometric data into a fixed-length feature vector and then projecting the feature vector onto a sequence of random subspaces that were derived from a user-specific pseudorandom number (PRN). This process is revocable and makes replacing biometrics as easy as replacing PRNs. The formulation has been verified under a number of scenarios (normal, stolen PRN, and compromised biometrics scenarios) using 2400 Facial Recognition Technology face images. The diversity property is also examined.

Original languageEnglish
Pages (from-to)1096-1106
Number of pages11
JournalIEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Volume37
Issue number5
DOIs
Publication statusPublished - 2007 Oct 1

Fingerprint

Privacy
Biometrics
Technology
Facial Recognition

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Software
  • Medicine(all)
  • Information Systems
  • Human-Computer Interaction
  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

@article{d059b08727874e879841351eb46fca58,
title = "Cancelable biometrics realization with multispace random projections",
abstract = "Biometric characteristics cannot be changed; therefore, the loss of privacy is permanent if they are ever compromised. This paper presents a two-factor cancelable formulation, where the biometric data are distorted in a revocable but nonreversible manner by first transforming the raw biometric data into a fixed-length feature vector and then projecting the feature vector onto a sequence of random subspaces that were derived from a user-specific pseudorandom number (PRN). This process is revocable and makes replacing biometrics as easy as replacing PRNs. The formulation has been verified under a number of scenarios (normal, stolen PRN, and compromised biometrics scenarios) using 2400 Facial Recognition Technology face images. The diversity property is also examined.",
author = "Teoh, {Andrew Beng Jin} and Yuang, {Chong Tze}",
year = "2007",
month = "10",
day = "1",
doi = "10.1109/TSMCB.2007.903538",
language = "English",
volume = "37",
pages = "1096--1106",
journal = "IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics",
issn = "1083-4419",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "5",

}

Cancelable biometrics realization with multispace random projections. / Teoh, Andrew Beng Jin; Yuang, Chong Tze.

In: IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, Vol. 37, No. 5, 01.10.2007, p. 1096-1106.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Cancelable biometrics realization with multispace random projections

AU - Teoh, Andrew Beng Jin

AU - Yuang, Chong Tze

PY - 2007/10/1

Y1 - 2007/10/1

N2 - Biometric characteristics cannot be changed; therefore, the loss of privacy is permanent if they are ever compromised. This paper presents a two-factor cancelable formulation, where the biometric data are distorted in a revocable but nonreversible manner by first transforming the raw biometric data into a fixed-length feature vector and then projecting the feature vector onto a sequence of random subspaces that were derived from a user-specific pseudorandom number (PRN). This process is revocable and makes replacing biometrics as easy as replacing PRNs. The formulation has been verified under a number of scenarios (normal, stolen PRN, and compromised biometrics scenarios) using 2400 Facial Recognition Technology face images. The diversity property is also examined.

AB - Biometric characteristics cannot be changed; therefore, the loss of privacy is permanent if they are ever compromised. This paper presents a two-factor cancelable formulation, where the biometric data are distorted in a revocable but nonreversible manner by first transforming the raw biometric data into a fixed-length feature vector and then projecting the feature vector onto a sequence of random subspaces that were derived from a user-specific pseudorandom number (PRN). This process is revocable and makes replacing biometrics as easy as replacing PRNs. The formulation has been verified under a number of scenarios (normal, stolen PRN, and compromised biometrics scenarios) using 2400 Facial Recognition Technology face images. The diversity property is also examined.

UR - http://www.scopus.com/inward/record.url?scp=35148885090&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=35148885090&partnerID=8YFLogxK

U2 - 10.1109/TSMCB.2007.903538

DO - 10.1109/TSMCB.2007.903538

M3 - Article

VL - 37

SP - 1096

EP - 1106

JO - IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

JF - IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

SN - 1083-4419

IS - 5

ER -