Multi-bits biometric string generation based on the likelyhood ratio

C. Chen; Raymond N.J. Veldhuis; T.A.M. Kevenaar; A.H.M. Akkermans

doi:10.1109/BTAS.2007.4401912

Multi-bits biometric string generation based on the likelyhood ratio

C. Chen, Raymond N.J. Veldhuis, T.A.M. Kevenaar, A.H.M. Akkermans

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

49 Citations (Scopus)

210 Downloads (Pure)

Abstract

Preserving the privacy of biometric information stored in biometric systems is becoming a key issue. An important element in privacy protecting biometric systems is the quantizer which transforms a normal biometric template into a binary string. In this paper, we present a user-specific quantization method based on a likelihood ratio approach (LQ). The bits generated from every feature are concatenated to form a fixed length binary string that can be hashed to protect its privacy. Experiments are carried out on both fingerprint data (FVC2000) and face data (FRGC). Results show that our proposed quantization method achieves a reasonably good performance in terms of FAR/FRR (when FAR is 10−4, the corresponding FRR are 16.7% and 5.77% for FVC2000 and FRGC, respectively).

Original language	Undefined
Title of host publication	IEEE conference on Biometrics: Theory, Applications and Systems
Editors	K.W. Bowyer, P.J. Flynn, V. Govindaraju, N. Ratha
Place of Publication	Los Alamitos, CA, USA
Publisher	IEEE
Pages	1-6
Number of pages	6
ISBN (Print)	978-1-4244-1597-7
DOIs	https://doi.org/10.1109/BTAS.2007.4401912
Publication status	Published - 29 Sept 2007
Event	First IEEE International Conference on Biometrics: Theory, Applications and Systems, BTAS 2007 - Washington, DC, USA Duration: 27 Sept 2007 → 29 Sept 2007

Publication series

Name
Publisher	IEEE
Number	Paper P-NS

Conference

Conference	First IEEE International Conference on Biometrics: Theory, Applications and Systems, BTAS 2007
Period	27/09/07 → 29/09/07
Other	27-29 September 2007

Keywords

SCS-Safety
METIS-245755
IR-61999
EWI-11335

Access to Document

10.1109/BTAS.2007.4401912

Cite this

@inproceedings{326a91cb50f94722a4ce12c26c43ef0c,

title = "Multi-bits biometric string generation based on the likelyhood ratio",

abstract = "Preserving the privacy of biometric information stored in biometric systems is becoming a key issue. An important element in privacy protecting biometric systems is the quantizer which transforms a normal biometric template into a binary string. In this paper, we present a user-specific quantization method based on a likelihood ratio approach (LQ). The bits generated from every feature are concatenated to form a fixed length binary string that can be hashed to protect its privacy. Experiments are carried out on both fingerprint data (FVC2000) and face data (FRGC). Results show that our proposed quantization method achieves a reasonably good performance in terms of FAR/FRR (when FAR is 10−4, the corresponding FRR are 16.7% and 5.77% for FVC2000 and FRGC, respectively).",

keywords = "SCS-Safety, METIS-245755, IR-61999, EWI-11335",

author = "C. Chen and Veldhuis, {Raymond N.J.} and T.A.M. Kevenaar and A.H.M. Akkermans",

year = "2007",

month = sep,

day = "29",

doi = "10.1109/BTAS.2007.4401912",

language = "Undefined",

isbn = "978-1-4244-1597-7",

publisher = "IEEE",

number = "Paper P-NS",

pages = "1--6",

editor = "K.W. Bowyer and P.J. Flynn and V. Govindaraju and N. Ratha",

booktitle = "IEEE conference on Biometrics: Theory, Applications and Systems",

address = "United States",

note = "First IEEE International Conference on Biometrics: Theory, Applications and Systems, BTAS 2007 ; Conference date: 27-09-2007 Through 29-09-2007",

}

Chen, C, Veldhuis, RNJ, Kevenaar, TAM & Akkermans, AHM 2007, Multi-bits biometric string generation based on the likelyhood ratio. in KW Bowyer, PJ Flynn, V Govindaraju & N Ratha (eds), IEEE conference on Biometrics: Theory, Applications and Systems. IEEE, Los Alamitos, CA, USA, pp. 1-6, First IEEE International Conference on Biometrics: Theory, Applications and Systems, BTAS 2007, 27/09/07. https://doi.org/10.1109/BTAS.2007.4401912

Multi-bits biometric string generation based on the likelyhood ratio. / Chen, C.; Veldhuis, Raymond N.J.; Kevenaar, T.A.M. et al.
IEEE conference on Biometrics: Theory, Applications and Systems. ed. / K.W. Bowyer; P.J. Flynn; V. Govindaraju; N. Ratha. Los Alamitos, CA, USA: IEEE, 2007. p. 1-6.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Multi-bits biometric string generation based on the likelyhood ratio

AU - Chen, C.

AU - Veldhuis, Raymond N.J.

AU - Kevenaar, T.A.M.

AU - Akkermans, A.H.M.

PY - 2007/9/29

Y1 - 2007/9/29

N2 - Preserving the privacy of biometric information stored in biometric systems is becoming a key issue. An important element in privacy protecting biometric systems is the quantizer which transforms a normal biometric template into a binary string. In this paper, we present a user-specific quantization method based on a likelihood ratio approach (LQ). The bits generated from every feature are concatenated to form a fixed length binary string that can be hashed to protect its privacy. Experiments are carried out on both fingerprint data (FVC2000) and face data (FRGC). Results show that our proposed quantization method achieves a reasonably good performance in terms of FAR/FRR (when FAR is 10−4, the corresponding FRR are 16.7% and 5.77% for FVC2000 and FRGC, respectively).

AB - Preserving the privacy of biometric information stored in biometric systems is becoming a key issue. An important element in privacy protecting biometric systems is the quantizer which transforms a normal biometric template into a binary string. In this paper, we present a user-specific quantization method based on a likelihood ratio approach (LQ). The bits generated from every feature are concatenated to form a fixed length binary string that can be hashed to protect its privacy. Experiments are carried out on both fingerprint data (FVC2000) and face data (FRGC). Results show that our proposed quantization method achieves a reasonably good performance in terms of FAR/FRR (when FAR is 10−4, the corresponding FRR are 16.7% and 5.77% for FVC2000 and FRGC, respectively).

KW - SCS-Safety

KW - METIS-245755

KW - IR-61999

KW - EWI-11335

U2 - 10.1109/BTAS.2007.4401912

DO - 10.1109/BTAS.2007.4401912

M3 - Conference contribution

SN - 978-1-4244-1597-7

SP - 1

EP - 6

BT - IEEE conference on Biometrics: Theory, Applications and Systems

A2 - Bowyer, K.W.

A2 - Flynn, P.J.

A2 - Govindaraju, V.

A2 - Ratha, N.

PB - IEEE

CY - Los Alamitos, CA, USA

T2 - First IEEE International Conference on Biometrics: Theory, Applications and Systems, BTAS 2007

Y2 - 27 September 2007 through 29 September 2007

ER -