A non-invertible Graph-based Hamming Embedding transform for fingerprint minutiae protection

Zhe Jin, Bok Min Goi, Yong Haur Tay, Beng Jin Teoh

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

Abstract

Biometrics is likely to provide a new level of security to various applications. Yet if the stored biometric template is compromised, invasion of user privacy could occur. Since biometric is irreplaceable and irrevocable, such an invasion often implies a permanent loss of identity. In this paper, a non-invertible Graph-based Hamming Embedding (GHE) technique is proposed to secure the minutia descriptors. The proposed technique initially employs Minutiae Vicinity Decomposition (MVD) to derive a set of geometrical invariant features from a set of fingerprint minutiae, and then globally embeds the MVD neighborhood structure into a Hamming space via solving a graph-based optimization problem. As a result, a secure binary template is generated. The resultant binary template enjoys three merits: 1) strong concealment of the minutia vicinity, which effectively protects the location and orientation of minutiae and ensures non-invertibility of the template. 2) improved or well preserved discriminability of descriptors in the Hamming space with respect to the Euclidean space. 3) quick matching due to pure involvement of bit-wise operations. Promising experimental results on FVC2002 database vindicate the feasibility of the proposed technique.

Original languageEnglish
Title of host publicationProceedings of the 2013 6th International Congress on Image and Signal Processing, CISP 2013
Pages1688-1693
Number of pages6
DOIs
Publication statusPublished - 2013 Dec 1
Event2013 6th International Congress on Image and Signal Processing, CISP 2013 - Hangzhou, China
Duration: 2013 Dec 162013 Dec 18

Publication series

NameProceedings of the 2013 6th International Congress on Image and Signal Processing, CISP 2013
Volume3

Other

Other2013 6th International Congress on Image and Signal Processing, CISP 2013
CountryChina
CityHangzhou
Period13/12/1613/12/18

Fingerprint

Biometrics
Decomposition

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Jin, Z., Goi, B. M., Tay, Y. H., & Teoh, B. J. (2013). A non-invertible Graph-based Hamming Embedding transform for fingerprint minutiae protection. In Proceedings of the 2013 6th International Congress on Image and Signal Processing, CISP 2013 (pp. 1688-1693). [6743948] (Proceedings of the 2013 6th International Congress on Image and Signal Processing, CISP 2013; Vol. 3). https://doi.org/10.1109/CISP.2013.6743948
Jin, Zhe ; Goi, Bok Min ; Tay, Yong Haur ; Teoh, Beng Jin. / A non-invertible Graph-based Hamming Embedding transform for fingerprint minutiae protection. Proceedings of the 2013 6th International Congress on Image and Signal Processing, CISP 2013. 2013. pp. 1688-1693 (Proceedings of the 2013 6th International Congress on Image and Signal Processing, CISP 2013).
@inproceedings{6e608e409e27443193c1da2ff5f56697,
title = "A non-invertible Graph-based Hamming Embedding transform for fingerprint minutiae protection",
abstract = "Biometrics is likely to provide a new level of security to various applications. Yet if the stored biometric template is compromised, invasion of user privacy could occur. Since biometric is irreplaceable and irrevocable, such an invasion often implies a permanent loss of identity. In this paper, a non-invertible Graph-based Hamming Embedding (GHE) technique is proposed to secure the minutia descriptors. The proposed technique initially employs Minutiae Vicinity Decomposition (MVD) to derive a set of geometrical invariant features from a set of fingerprint minutiae, and then globally embeds the MVD neighborhood structure into a Hamming space via solving a graph-based optimization problem. As a result, a secure binary template is generated. The resultant binary template enjoys three merits: 1) strong concealment of the minutia vicinity, which effectively protects the location and orientation of minutiae and ensures non-invertibility of the template. 2) improved or well preserved discriminability of descriptors in the Hamming space with respect to the Euclidean space. 3) quick matching due to pure involvement of bit-wise operations. Promising experimental results on FVC2002 database vindicate the feasibility of the proposed technique.",
author = "Zhe Jin and Goi, {Bok Min} and Tay, {Yong Haur} and Teoh, {Beng Jin}",
year = "2013",
month = "12",
day = "1",
doi = "10.1109/CISP.2013.6743948",
language = "English",
isbn = "9781479927647",
series = "Proceedings of the 2013 6th International Congress on Image and Signal Processing, CISP 2013",
pages = "1688--1693",
booktitle = "Proceedings of the 2013 6th International Congress on Image and Signal Processing, CISP 2013",

}

Jin, Z, Goi, BM, Tay, YH & Teoh, BJ 2013, A non-invertible Graph-based Hamming Embedding transform for fingerprint minutiae protection. in Proceedings of the 2013 6th International Congress on Image and Signal Processing, CISP 2013., 6743948, Proceedings of the 2013 6th International Congress on Image and Signal Processing, CISP 2013, vol. 3, pp. 1688-1693, 2013 6th International Congress on Image and Signal Processing, CISP 2013, Hangzhou, China, 13/12/16. https://doi.org/10.1109/CISP.2013.6743948

A non-invertible Graph-based Hamming Embedding transform for fingerprint minutiae protection. / Jin, Zhe; Goi, Bok Min; Tay, Yong Haur; Teoh, Beng Jin.

Proceedings of the 2013 6th International Congress on Image and Signal Processing, CISP 2013. 2013. p. 1688-1693 6743948 (Proceedings of the 2013 6th International Congress on Image and Signal Processing, CISP 2013; Vol. 3).

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

TY - GEN

T1 - A non-invertible Graph-based Hamming Embedding transform for fingerprint minutiae protection

AU - Jin, Zhe

AU - Goi, Bok Min

AU - Tay, Yong Haur

AU - Teoh, Beng Jin

PY - 2013/12/1

Y1 - 2013/12/1

N2 - Biometrics is likely to provide a new level of security to various applications. Yet if the stored biometric template is compromised, invasion of user privacy could occur. Since biometric is irreplaceable and irrevocable, such an invasion often implies a permanent loss of identity. In this paper, a non-invertible Graph-based Hamming Embedding (GHE) technique is proposed to secure the minutia descriptors. The proposed technique initially employs Minutiae Vicinity Decomposition (MVD) to derive a set of geometrical invariant features from a set of fingerprint minutiae, and then globally embeds the MVD neighborhood structure into a Hamming space via solving a graph-based optimization problem. As a result, a secure binary template is generated. The resultant binary template enjoys three merits: 1) strong concealment of the minutia vicinity, which effectively protects the location and orientation of minutiae and ensures non-invertibility of the template. 2) improved or well preserved discriminability of descriptors in the Hamming space with respect to the Euclidean space. 3) quick matching due to pure involvement of bit-wise operations. Promising experimental results on FVC2002 database vindicate the feasibility of the proposed technique.

AB - Biometrics is likely to provide a new level of security to various applications. Yet if the stored biometric template is compromised, invasion of user privacy could occur. Since biometric is irreplaceable and irrevocable, such an invasion often implies a permanent loss of identity. In this paper, a non-invertible Graph-based Hamming Embedding (GHE) technique is proposed to secure the minutia descriptors. The proposed technique initially employs Minutiae Vicinity Decomposition (MVD) to derive a set of geometrical invariant features from a set of fingerprint minutiae, and then globally embeds the MVD neighborhood structure into a Hamming space via solving a graph-based optimization problem. As a result, a secure binary template is generated. The resultant binary template enjoys three merits: 1) strong concealment of the minutia vicinity, which effectively protects the location and orientation of minutiae and ensures non-invertibility of the template. 2) improved or well preserved discriminability of descriptors in the Hamming space with respect to the Euclidean space. 3) quick matching due to pure involvement of bit-wise operations. Promising experimental results on FVC2002 database vindicate the feasibility of the proposed technique.

UR - http://www.scopus.com/inward/record.url?scp=84897748649&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84897748649&partnerID=8YFLogxK

U2 - 10.1109/CISP.2013.6743948

DO - 10.1109/CISP.2013.6743948

M3 - Conference contribution

SN - 9781479927647

T3 - Proceedings of the 2013 6th International Congress on Image and Signal Processing, CISP 2013

SP - 1688

EP - 1693

BT - Proceedings of the 2013 6th International Congress on Image and Signal Processing, CISP 2013

ER -

Jin Z, Goi BM, Tay YH, Teoh BJ. A non-invertible Graph-based Hamming Embedding transform for fingerprint minutiae protection. In Proceedings of the 2013 6th International Congress on Image and Signal Processing, CISP 2013. 2013. p. 1688-1693. 6743948. (Proceedings of the 2013 6th International Congress on Image and Signal Processing, CISP 2013). https://doi.org/10.1109/CISP.2013.6743948