A method to enhance face biometric security

Youngsung Kim, Kar Ann Toh

Research output: Chapter in Book/Report/Conference proceedingConference contribution

16 Citations (Scopus)

Abstract

In cancelable biometrics, a template undergoes a random-like transformation process such that it is disposable and a new template for the same identity can be re-generated for new usage. However, existing works do not consider control of verification performance and identity concealment at the same time. In this paper, we propose a method which can boost the verification performance of face biometric via two steps: using an efficient feature extraction transformation, and using an error minimizing template transformation. An extended Random Projection of face data improves the feature extraction efficiency in the first step. A near optimal transformation of the face template is next generated from iterative steps of gradient descent algorithm based on an error rate formulation. For experimentation, we adopted face images from AR and BERC databases where the face images were collected under various external conditions. From these face databases, we show an improved verification performance in terms of test equal error rate (EER), at the same time hiding the face identity based on template transformation. This work contributes to establishment of an algorithm for effective cancelable face template generation as well as verification performance enhancement.

Original languageEnglish
Title of host publicationIEEE Conference on Biometrics
Subtitle of host publicationTheory, Applications and Systems, BTAS'07
DOIs
Publication statusPublished - 2007 Dec 1
Event1st IEEE International Conference on Biometrics: Theory, Applications, and Systems, BTAS '07 - Crystal City, VA, United States
Duration: 2007 Sep 272007 Sep 29

Publication series

NameIEEE Conference on Biometrics: Theory, Applications and Systems, BTAS'07

Other

Other1st IEEE International Conference on Biometrics: Theory, Applications, and Systems, BTAS '07
CountryUnited States
CityCrystal City, VA
Period07/9/2707/9/29

Fingerprint

Biometrics
Feature extraction

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Kim, Y., & Toh, K. A. (2007). A method to enhance face biometric security. In IEEE Conference on Biometrics: Theory, Applications and Systems, BTAS'07 [4401913] (IEEE Conference on Biometrics: Theory, Applications and Systems, BTAS'07). https://doi.org/10.1109/BTAS.2007.4401913
Kim, Youngsung ; Toh, Kar Ann. / A method to enhance face biometric security. IEEE Conference on Biometrics: Theory, Applications and Systems, BTAS'07. 2007. (IEEE Conference on Biometrics: Theory, Applications and Systems, BTAS'07).
@inproceedings{1987a3852a5543ecadd7919a3a069bd8,
title = "A method to enhance face biometric security",
abstract = "In cancelable biometrics, a template undergoes a random-like transformation process such that it is disposable and a new template for the same identity can be re-generated for new usage. However, existing works do not consider control of verification performance and identity concealment at the same time. In this paper, we propose a method which can boost the verification performance of face biometric via two steps: using an efficient feature extraction transformation, and using an error minimizing template transformation. An extended Random Projection of face data improves the feature extraction efficiency in the first step. A near optimal transformation of the face template is next generated from iterative steps of gradient descent algorithm based on an error rate formulation. For experimentation, we adopted face images from AR and BERC databases where the face images were collected under various external conditions. From these face databases, we show an improved verification performance in terms of test equal error rate (EER), at the same time hiding the face identity based on template transformation. This work contributes to establishment of an algorithm for effective cancelable face template generation as well as verification performance enhancement.",
author = "Youngsung Kim and Toh, {Kar Ann}",
year = "2007",
month = "12",
day = "1",
doi = "10.1109/BTAS.2007.4401913",
language = "English",
isbn = "9781424415977",
series = "IEEE Conference on Biometrics: Theory, Applications and Systems, BTAS'07",
booktitle = "IEEE Conference on Biometrics",

}

Kim, Y & Toh, KA 2007, A method to enhance face biometric security. in IEEE Conference on Biometrics: Theory, Applications and Systems, BTAS'07., 4401913, IEEE Conference on Biometrics: Theory, Applications and Systems, BTAS'07, 1st IEEE International Conference on Biometrics: Theory, Applications, and Systems, BTAS '07, Crystal City, VA, United States, 07/9/27. https://doi.org/10.1109/BTAS.2007.4401913

A method to enhance face biometric security. / Kim, Youngsung; Toh, Kar Ann.

IEEE Conference on Biometrics: Theory, Applications and Systems, BTAS'07. 2007. 4401913 (IEEE Conference on Biometrics: Theory, Applications and Systems, BTAS'07).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - A method to enhance face biometric security

AU - Kim, Youngsung

AU - Toh, Kar Ann

PY - 2007/12/1

Y1 - 2007/12/1

N2 - In cancelable biometrics, a template undergoes a random-like transformation process such that it is disposable and a new template for the same identity can be re-generated for new usage. However, existing works do not consider control of verification performance and identity concealment at the same time. In this paper, we propose a method which can boost the verification performance of face biometric via two steps: using an efficient feature extraction transformation, and using an error minimizing template transformation. An extended Random Projection of face data improves the feature extraction efficiency in the first step. A near optimal transformation of the face template is next generated from iterative steps of gradient descent algorithm based on an error rate formulation. For experimentation, we adopted face images from AR and BERC databases where the face images were collected under various external conditions. From these face databases, we show an improved verification performance in terms of test equal error rate (EER), at the same time hiding the face identity based on template transformation. This work contributes to establishment of an algorithm for effective cancelable face template generation as well as verification performance enhancement.

AB - In cancelable biometrics, a template undergoes a random-like transformation process such that it is disposable and a new template for the same identity can be re-generated for new usage. However, existing works do not consider control of verification performance and identity concealment at the same time. In this paper, we propose a method which can boost the verification performance of face biometric via two steps: using an efficient feature extraction transformation, and using an error minimizing template transformation. An extended Random Projection of face data improves the feature extraction efficiency in the first step. A near optimal transformation of the face template is next generated from iterative steps of gradient descent algorithm based on an error rate formulation. For experimentation, we adopted face images from AR and BERC databases where the face images were collected under various external conditions. From these face databases, we show an improved verification performance in terms of test equal error rate (EER), at the same time hiding the face identity based on template transformation. This work contributes to establishment of an algorithm for effective cancelable face template generation as well as verification performance enhancement.

UR - http://www.scopus.com/inward/record.url?scp=48649097707&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=48649097707&partnerID=8YFLogxK

U2 - 10.1109/BTAS.2007.4401913

DO - 10.1109/BTAS.2007.4401913

M3 - Conference contribution

AN - SCOPUS:48649097707

SN - 9781424415977

T3 - IEEE Conference on Biometrics: Theory, Applications and Systems, BTAS'07

BT - IEEE Conference on Biometrics

ER -

Kim Y, Toh KA. A method to enhance face biometric security. In IEEE Conference on Biometrics: Theory, Applications and Systems, BTAS'07. 2007. 4401913. (IEEE Conference on Biometrics: Theory, Applications and Systems, BTAS'07). https://doi.org/10.1109/BTAS.2007.4401913