A changeable biometric system that uses parts-based localized representation for face recognition

Jongsun Kim, Chulhan Lee, Jaihie Kim

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

1 Citation (Scopus)

Abstract

Biometric data cannot be changed or canceled if they are compromised. To cope with this problem, changeable biometric systems that use transformed biometric data instead of original data have recently been introduced. In this paper, we propose a changeable biometric system for face recognition that uses LNMF (Local Non-negative Matrix Factorization), or parts-based localized representation. Two different sets of LNMF bases can be computed from given training images when training them twice and two different LNMF feature vectors can then be extracted from an input face image using these LNMF bases. The two feature vectors are scrambled randomly and a new transformed feature vector can be generated by the addition of the two feature vectors. The scrambling rule is determined by a given user's PIN, and when the transformed feature vector is compromised, it is replaced by using a new scrambling rule. Because the transformed template is generated by the addition of two vectors, the two different original LNMF feature vectors cannot be recovered from the transformed feature vector. Experimental results show that the proposed method performs better than the PCA and original LNMF-based methods. Also the transformed feature vector satisfies the requirement of changeability.

Original languageEnglish
Title of host publication2007 IEEE Workshop on Automatic Identification Advanced Technologies - Proceedings
Pages165-168
Number of pages4
DOIs
Publication statusPublished - 2007 Oct 2
Event2007 IEEE Workshop on Automatic Identification Advanced Technologies, AUTOID 2007 - Alghero, Italy
Duration: 2007 Jun 72007 Jun 8

Publication series

Name2007 IEEE Workshop on Automatic Identification Advanced Technologies - Proceedings

Other

Other2007 IEEE Workshop on Automatic Identification Advanced Technologies, AUTOID 2007
CountryItaly
CityAlghero
Period07/6/707/6/8

Fingerprint

Biometrics
Face recognition
Factorization

All Science Journal Classification (ASJC) codes

  • Computer Science(all)

Cite this

Kim, J., Lee, C., & Kim, J. (2007). A changeable biometric system that uses parts-based localized representation for face recognition. In 2007 IEEE Workshop on Automatic Identification Advanced Technologies - Proceedings (pp. 165-168). [4263234] (2007 IEEE Workshop on Automatic Identification Advanced Technologies - Proceedings). https://doi.org/10.1109/AUTOID.2007.380613
Kim, Jongsun ; Lee, Chulhan ; Kim, Jaihie. / A changeable biometric system that uses parts-based localized representation for face recognition. 2007 IEEE Workshop on Automatic Identification Advanced Technologies - Proceedings. 2007. pp. 165-168 (2007 IEEE Workshop on Automatic Identification Advanced Technologies - Proceedings).
@inproceedings{7658ea6cab9c41308d06d76eb5462497,
title = "A changeable biometric system that uses parts-based localized representation for face recognition",
abstract = "Biometric data cannot be changed or canceled if they are compromised. To cope with this problem, changeable biometric systems that use transformed biometric data instead of original data have recently been introduced. In this paper, we propose a changeable biometric system for face recognition that uses LNMF (Local Non-negative Matrix Factorization), or parts-based localized representation. Two different sets of LNMF bases can be computed from given training images when training them twice and two different LNMF feature vectors can then be extracted from an input face image using these LNMF bases. The two feature vectors are scrambled randomly and a new transformed feature vector can be generated by the addition of the two feature vectors. The scrambling rule is determined by a given user's PIN, and when the transformed feature vector is compromised, it is replaced by using a new scrambling rule. Because the transformed template is generated by the addition of two vectors, the two different original LNMF feature vectors cannot be recovered from the transformed feature vector. Experimental results show that the proposed method performs better than the PCA and original LNMF-based methods. Also the transformed feature vector satisfies the requirement of changeability.",
author = "Jongsun Kim and Chulhan Lee and Jaihie Kim",
year = "2007",
month = "10",
day = "2",
doi = "10.1109/AUTOID.2007.380613",
language = "English",
isbn = "1424412994",
series = "2007 IEEE Workshop on Automatic Identification Advanced Technologies - Proceedings",
pages = "165--168",
booktitle = "2007 IEEE Workshop on Automatic Identification Advanced Technologies - Proceedings",

}

Kim, J, Lee, C & Kim, J 2007, A changeable biometric system that uses parts-based localized representation for face recognition. in 2007 IEEE Workshop on Automatic Identification Advanced Technologies - Proceedings., 4263234, 2007 IEEE Workshop on Automatic Identification Advanced Technologies - Proceedings, pp. 165-168, 2007 IEEE Workshop on Automatic Identification Advanced Technologies, AUTOID 2007, Alghero, Italy, 07/6/7. https://doi.org/10.1109/AUTOID.2007.380613

A changeable biometric system that uses parts-based localized representation for face recognition. / Kim, Jongsun; Lee, Chulhan; Kim, Jaihie.

2007 IEEE Workshop on Automatic Identification Advanced Technologies - Proceedings. 2007. p. 165-168 4263234 (2007 IEEE Workshop on Automatic Identification Advanced Technologies - Proceedings).

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

TY - GEN

T1 - A changeable biometric system that uses parts-based localized representation for face recognition

AU - Kim, Jongsun

AU - Lee, Chulhan

AU - Kim, Jaihie

PY - 2007/10/2

Y1 - 2007/10/2

N2 - Biometric data cannot be changed or canceled if they are compromised. To cope with this problem, changeable biometric systems that use transformed biometric data instead of original data have recently been introduced. In this paper, we propose a changeable biometric system for face recognition that uses LNMF (Local Non-negative Matrix Factorization), or parts-based localized representation. Two different sets of LNMF bases can be computed from given training images when training them twice and two different LNMF feature vectors can then be extracted from an input face image using these LNMF bases. The two feature vectors are scrambled randomly and a new transformed feature vector can be generated by the addition of the two feature vectors. The scrambling rule is determined by a given user's PIN, and when the transformed feature vector is compromised, it is replaced by using a new scrambling rule. Because the transformed template is generated by the addition of two vectors, the two different original LNMF feature vectors cannot be recovered from the transformed feature vector. Experimental results show that the proposed method performs better than the PCA and original LNMF-based methods. Also the transformed feature vector satisfies the requirement of changeability.

AB - Biometric data cannot be changed or canceled if they are compromised. To cope with this problem, changeable biometric systems that use transformed biometric data instead of original data have recently been introduced. In this paper, we propose a changeable biometric system for face recognition that uses LNMF (Local Non-negative Matrix Factorization), or parts-based localized representation. Two different sets of LNMF bases can be computed from given training images when training them twice and two different LNMF feature vectors can then be extracted from an input face image using these LNMF bases. The two feature vectors are scrambled randomly and a new transformed feature vector can be generated by the addition of the two feature vectors. The scrambling rule is determined by a given user's PIN, and when the transformed feature vector is compromised, it is replaced by using a new scrambling rule. Because the transformed template is generated by the addition of two vectors, the two different original LNMF feature vectors cannot be recovered from the transformed feature vector. Experimental results show that the proposed method performs better than the PCA and original LNMF-based methods. Also the transformed feature vector satisfies the requirement of changeability.

UR - http://www.scopus.com/inward/record.url?scp=34748816403&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34748816403&partnerID=8YFLogxK

U2 - 10.1109/AUTOID.2007.380613

DO - 10.1109/AUTOID.2007.380613

M3 - Conference contribution

AN - SCOPUS:34748816403

SN - 1424412994

SN - 9781424412990

T3 - 2007 IEEE Workshop on Automatic Identification Advanced Technologies - Proceedings

SP - 165

EP - 168

BT - 2007 IEEE Workshop on Automatic Identification Advanced Technologies - Proceedings

ER -

Kim J, Lee C, Kim J. A changeable biometric system that uses parts-based localized representation for face recognition. In 2007 IEEE Workshop on Automatic Identification Advanced Technologies - Proceedings. 2007. p. 165-168. 4263234. (2007 IEEE Workshop on Automatic Identification Advanced Technologies - Proceedings). https://doi.org/10.1109/AUTOID.2007.380613