Biometric bits extraction through phase quantization based on feature level fusion

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Biometric bits extraction has emerged as an essential technique for the study of biometric template protection as well as biometric cryptosystems. In this paper, we present a non-invertible but revocable bits extraction technique by means of quantizing the facial data from two feature extractors in the phase domain, which we coin as aligned feature-level fusion phase quantization (AFPQ). In this technique, we utilize helper data to achieve the revocability requirement of bits extraction. The feature averaging and remainder normalization technique are integrated with the helper data to reduce feature variance within the same individual and increase the distinctiveness of bit strings of different individuals to achieve good recognition performance. A scenario in which the system is compromised by an adversary is also considered. As a generic technique, AFPQ can be easily extended to multiple different biometric modalities.

Original languageEnglish
Pages (from-to)255-273
Number of pages19
JournalTelecommunication Systems
Volume47
Issue number3-4
DOIs
Publication statusPublished - 2011 Aug 1

Fingerprint

Biometrics
Fusion reactions
Cryptography

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

Cite this

@article{256b1b467eb34c0ba8379a92d1c5e26e,
title = "Biometric bits extraction through phase quantization based on feature level fusion",
abstract = "Biometric bits extraction has emerged as an essential technique for the study of biometric template protection as well as biometric cryptosystems. In this paper, we present a non-invertible but revocable bits extraction technique by means of quantizing the facial data from two feature extractors in the phase domain, which we coin as aligned feature-level fusion phase quantization (AFPQ). In this technique, we utilize helper data to achieve the revocability requirement of bits extraction. The feature averaging and remainder normalization technique are integrated with the helper data to reduce feature variance within the same individual and increase the distinctiveness of bit strings of different individuals to achieve good recognition performance. A scenario in which the system is compromised by an adversary is also considered. As a generic technique, AFPQ can be easily extended to multiple different biometric modalities.",
author = "Hyunggu Lee and Teoh, {Andrew Beng Jin} and Jaihie Kim",
year = "2011",
month = "8",
day = "1",
doi = "10.1007/s11235-010-9317-z",
language = "English",
volume = "47",
pages = "255--273",
journal = "Telecommunication Systems",
issn = "1018-4864",
publisher = "Springer Netherlands",
number = "3-4",

}

Biometric bits extraction through phase quantization based on feature level fusion. / Lee, Hyunggu; Teoh, Andrew Beng Jin; Kim, Jaihie.

In: Telecommunication Systems, Vol. 47, No. 3-4, 01.08.2011, p. 255-273.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Biometric bits extraction through phase quantization based on feature level fusion

AU - Lee, Hyunggu

AU - Teoh, Andrew Beng Jin

AU - Kim, Jaihie

PY - 2011/8/1

Y1 - 2011/8/1

N2 - Biometric bits extraction has emerged as an essential technique for the study of biometric template protection as well as biometric cryptosystems. In this paper, we present a non-invertible but revocable bits extraction technique by means of quantizing the facial data from two feature extractors in the phase domain, which we coin as aligned feature-level fusion phase quantization (AFPQ). In this technique, we utilize helper data to achieve the revocability requirement of bits extraction. The feature averaging and remainder normalization technique are integrated with the helper data to reduce feature variance within the same individual and increase the distinctiveness of bit strings of different individuals to achieve good recognition performance. A scenario in which the system is compromised by an adversary is also considered. As a generic technique, AFPQ can be easily extended to multiple different biometric modalities.

AB - Biometric bits extraction has emerged as an essential technique for the study of biometric template protection as well as biometric cryptosystems. In this paper, we present a non-invertible but revocable bits extraction technique by means of quantizing the facial data from two feature extractors in the phase domain, which we coin as aligned feature-level fusion phase quantization (AFPQ). In this technique, we utilize helper data to achieve the revocability requirement of bits extraction. The feature averaging and remainder normalization technique are integrated with the helper data to reduce feature variance within the same individual and increase the distinctiveness of bit strings of different individuals to achieve good recognition performance. A scenario in which the system is compromised by an adversary is also considered. As a generic technique, AFPQ can be easily extended to multiple different biometric modalities.

UR - http://www.scopus.com/inward/record.url?scp=79958162287&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79958162287&partnerID=8YFLogxK

U2 - 10.1007/s11235-010-9317-z

DO - 10.1007/s11235-010-9317-z

M3 - Article

AN - SCOPUS:79958162287

VL - 47

SP - 255

EP - 273

JO - Telecommunication Systems

JF - Telecommunication Systems

SN - 1018-4864

IS - 3-4

ER -