Changeable biometrics for appearance based face recognition

Minyi Jeong, Chulhan Lee, Jongsun Kim, Jeung Yoon Choi, Kar Ann Toh, Jaihie Kim

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

24 Citations (Scopus)

Abstract

To enhance security and privacy in biometrics, changeable (or cancelable) biometrics have recently been introduced. The idea is to transform a biometric signal or feature into a new one for enrollment and matching. In this paper, we proposed changeable biometrics for face recognition using an appearance based approach. PCA and ICA coefficient vectors extracted from an input face image are normalized using their norm. The two normalized vectors are scrambled randomly and a new transformed face coefficient vector (transformed template) is generated by addition of the two normalized vectors. When a transformed template is compromised, it is replaced by using a new scrambling rule. Because the transformed template is generated by the addition of two vectors, the original PCA and ICA coefficients cannot be recovered from the transformed coefficients. In our experiment, we compared the performance between the cases when PCA and ICA coefficient vectors are used for verification and when the transformed coefficient vectors are used for verification.

Original languageEnglish
Title of host publicationBiometrics Symposium, BCC 2006
DOIs
Publication statusPublished - 2006 Dec 1
Event2006 Biometrics Symposium: Special Session on Research at the Biometric Consortium Conference, BCC - Baltimore, MD, United States
Duration: 2006 Sep 192006 Sep 21

Publication series

NameBiometrics Symposium, BCC 2006

Other

Other2006 Biometrics Symposium: Special Session on Research at the Biometric Consortium Conference, BCC
CountryUnited States
CityBaltimore, MD
Period06/9/1906/9/21

Fingerprint

Passive Cutaneous Anaphylaxis
Biometrics
biometry
Face recognition
Independent component analysis
Privacy
Facial Recognition

All Science Journal Classification (ASJC) codes

  • Agricultural and Biological Sciences(all)
  • Computational Theory and Mathematics
  • Computer Science Applications

Cite this

Jeong, M., Lee, C., Kim, J., Choi, J. Y., Toh, K. A., & Kim, J. (2006). Changeable biometrics for appearance based face recognition. In Biometrics Symposium, BCC 2006 [4341629] (Biometrics Symposium, BCC 2006). https://doi.org/10.1109/BCC.2006.4341629
Jeong, Minyi ; Lee, Chulhan ; Kim, Jongsun ; Choi, Jeung Yoon ; Toh, Kar Ann ; Kim, Jaihie. / Changeable biometrics for appearance based face recognition. Biometrics Symposium, BCC 2006. 2006. (Biometrics Symposium, BCC 2006).
@inproceedings{dc73c91a9b4a4cd98551aa76b0aa4dc1,
title = "Changeable biometrics for appearance based face recognition",
abstract = "To enhance security and privacy in biometrics, changeable (or cancelable) biometrics have recently been introduced. The idea is to transform a biometric signal or feature into a new one for enrollment and matching. In this paper, we proposed changeable biometrics for face recognition using an appearance based approach. PCA and ICA coefficient vectors extracted from an input face image are normalized using their norm. The two normalized vectors are scrambled randomly and a new transformed face coefficient vector (transformed template) is generated by addition of the two normalized vectors. When a transformed template is compromised, it is replaced by using a new scrambling rule. Because the transformed template is generated by the addition of two vectors, the original PCA and ICA coefficients cannot be recovered from the transformed coefficients. In our experiment, we compared the performance between the cases when PCA and ICA coefficient vectors are used for verification and when the transformed coefficient vectors are used for verification.",
author = "Minyi Jeong and Chulhan Lee and Jongsun Kim and Choi, {Jeung Yoon} and Toh, {Kar Ann} and Jaihie Kim",
year = "2006",
month = "12",
day = "1",
doi = "10.1109/BCC.2006.4341629",
language = "English",
isbn = "1424404878",
series = "Biometrics Symposium, BCC 2006",
booktitle = "Biometrics Symposium, BCC 2006",

}

Jeong, M, Lee, C, Kim, J, Choi, JY, Toh, KA & Kim, J 2006, Changeable biometrics for appearance based face recognition. in Biometrics Symposium, BCC 2006., 4341629, Biometrics Symposium, BCC 2006, 2006 Biometrics Symposium: Special Session on Research at the Biometric Consortium Conference, BCC, Baltimore, MD, United States, 06/9/19. https://doi.org/10.1109/BCC.2006.4341629

Changeable biometrics for appearance based face recognition. / Jeong, Minyi; Lee, Chulhan; Kim, Jongsun; Choi, Jeung Yoon; Toh, Kar Ann; Kim, Jaihie.

Biometrics Symposium, BCC 2006. 2006. 4341629 (Biometrics Symposium, BCC 2006).

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

TY - GEN

T1 - Changeable biometrics for appearance based face recognition

AU - Jeong, Minyi

AU - Lee, Chulhan

AU - Kim, Jongsun

AU - Choi, Jeung Yoon

AU - Toh, Kar Ann

AU - Kim, Jaihie

PY - 2006/12/1

Y1 - 2006/12/1

N2 - To enhance security and privacy in biometrics, changeable (or cancelable) biometrics have recently been introduced. The idea is to transform a biometric signal or feature into a new one for enrollment and matching. In this paper, we proposed changeable biometrics for face recognition using an appearance based approach. PCA and ICA coefficient vectors extracted from an input face image are normalized using their norm. The two normalized vectors are scrambled randomly and a new transformed face coefficient vector (transformed template) is generated by addition of the two normalized vectors. When a transformed template is compromised, it is replaced by using a new scrambling rule. Because the transformed template is generated by the addition of two vectors, the original PCA and ICA coefficients cannot be recovered from the transformed coefficients. In our experiment, we compared the performance between the cases when PCA and ICA coefficient vectors are used for verification and when the transformed coefficient vectors are used for verification.

AB - To enhance security and privacy in biometrics, changeable (or cancelable) biometrics have recently been introduced. The idea is to transform a biometric signal or feature into a new one for enrollment and matching. In this paper, we proposed changeable biometrics for face recognition using an appearance based approach. PCA and ICA coefficient vectors extracted from an input face image are normalized using their norm. The two normalized vectors are scrambled randomly and a new transformed face coefficient vector (transformed template) is generated by addition of the two normalized vectors. When a transformed template is compromised, it is replaced by using a new scrambling rule. Because the transformed template is generated by the addition of two vectors, the original PCA and ICA coefficients cannot be recovered from the transformed coefficients. In our experiment, we compared the performance between the cases when PCA and ICA coefficient vectors are used for verification and when the transformed coefficient vectors are used for verification.

UR - http://www.scopus.com/inward/record.url?scp=50249138275&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=50249138275&partnerID=8YFLogxK

U2 - 10.1109/BCC.2006.4341629

DO - 10.1109/BCC.2006.4341629

M3 - Conference contribution

AN - SCOPUS:50249138275

SN - 1424404878

SN - 9781424404872

T3 - Biometrics Symposium, BCC 2006

BT - Biometrics Symposium, BCC 2006

ER -

Jeong M, Lee C, Kim J, Choi JY, Toh KA, Kim J. Changeable biometrics for appearance based face recognition. In Biometrics Symposium, BCC 2006. 2006. 4341629. (Biometrics Symposium, BCC 2006). https://doi.org/10.1109/BCC.2006.4341629