A performance driven methodology for cancelable face templates generation

Youngsung Kim, Beng Jin Teoh, Kar Ann Toh

Research output: Contribution to journalArticle

15 Citations (Scopus)

Abstract

In this paper, we propose a performance driven methodology for cancelable face templates generation. This is to address the issue of satisfying both the security and performance requirements at the same time. Essentially, the methodology consists of two transformations namely, an efficient feature extraction transformation and an error minimizing template transformation. The first transformation is achieved via a modified sparse random projection which extracts and transforms essential face features into cancelable templates. The second transformation is realized through a direct objective formulation to minimize the system's total error rate. In order to facilitate convergence of the resulted minimization search, a modified sigmoid is proposed for an error counting step function approximation. Using two publicly available face databases, we empirically show an improved verification performance in terms of the equal error rate while hiding the face identity simultaneously.

Original languageEnglish
Pages (from-to)2544-2559
Number of pages16
JournalPattern Recognition
Volume43
Issue number7
DOIs
Publication statusPublished - 2010 Jul 1

Fingerprint

Feature extraction

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

@article{692e37d693644a578ceee803e8dbcbe8,
title = "A performance driven methodology for cancelable face templates generation",
abstract = "In this paper, we propose a performance driven methodology for cancelable face templates generation. This is to address the issue of satisfying both the security and performance requirements at the same time. Essentially, the methodology consists of two transformations namely, an efficient feature extraction transformation and an error minimizing template transformation. The first transformation is achieved via a modified sparse random projection which extracts and transforms essential face features into cancelable templates. The second transformation is realized through a direct objective formulation to minimize the system's total error rate. In order to facilitate convergence of the resulted minimization search, a modified sigmoid is proposed for an error counting step function approximation. Using two publicly available face databases, we empirically show an improved verification performance in terms of the equal error rate while hiding the face identity simultaneously.",
author = "Youngsung Kim and Teoh, {Beng Jin} and Toh, {Kar Ann}",
year = "2010",
month = "7",
day = "1",
doi = "10.1016/j.patcog.2010.02.001",
language = "English",
volume = "43",
pages = "2544--2559",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "Elsevier Limited",
number = "7",

}

A performance driven methodology for cancelable face templates generation. / Kim, Youngsung; Teoh, Beng Jin; Toh, Kar Ann.

In: Pattern Recognition, Vol. 43, No. 7, 01.07.2010, p. 2544-2559.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A performance driven methodology for cancelable face templates generation

AU - Kim, Youngsung

AU - Teoh, Beng Jin

AU - Toh, Kar Ann

PY - 2010/7/1

Y1 - 2010/7/1

N2 - In this paper, we propose a performance driven methodology for cancelable face templates generation. This is to address the issue of satisfying both the security and performance requirements at the same time. Essentially, the methodology consists of two transformations namely, an efficient feature extraction transformation and an error minimizing template transformation. The first transformation is achieved via a modified sparse random projection which extracts and transforms essential face features into cancelable templates. The second transformation is realized through a direct objective formulation to minimize the system's total error rate. In order to facilitate convergence of the resulted minimization search, a modified sigmoid is proposed for an error counting step function approximation. Using two publicly available face databases, we empirically show an improved verification performance in terms of the equal error rate while hiding the face identity simultaneously.

AB - In this paper, we propose a performance driven methodology for cancelable face templates generation. This is to address the issue of satisfying both the security and performance requirements at the same time. Essentially, the methodology consists of two transformations namely, an efficient feature extraction transformation and an error minimizing template transformation. The first transformation is achieved via a modified sparse random projection which extracts and transforms essential face features into cancelable templates. The second transformation is realized through a direct objective formulation to minimize the system's total error rate. In order to facilitate convergence of the resulted minimization search, a modified sigmoid is proposed for an error counting step function approximation. Using two publicly available face databases, we empirically show an improved verification performance in terms of the equal error rate while hiding the face identity simultaneously.

UR - http://www.scopus.com/inward/record.url?scp=77949488110&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77949488110&partnerID=8YFLogxK

U2 - 10.1016/j.patcog.2010.02.001

DO - 10.1016/j.patcog.2010.02.001

M3 - Article

VL - 43

SP - 2544

EP - 2559

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

IS - 7

ER -