Kernel PCA enabled bit-string representation for minutiae-based cancellable fingerprint template

Wei Jing Wong, Beng Jin Teoh, Yau Hee Kho, M. L. Dennis Wong

Research output: Contribution to journalArticle

23 Citations (Scopus)

Abstract

Minutiae set is one of the prevalent features used to represent a fingerprint. Many minutiae protection schemes have been proposed in recent literature, but only a few have demonstrated successful conversion from minutiae set to fixed-length bit-string. In this paper, we develop a fixed-length binary cancellable fingerprint template generation scheme based on a minutia descriptor known as the multi-line code (MLC). While retaining the core of MLC algorithm, we transform the unordered and variable-size MLC template into an ordered and fixed-length bit-string using kernel principal components analysis (KPCA) and state-of-the-art binarization techniques. The construction of a proper kernel suited for the scenario was validated using Mercer's Theorem. Evaluation of the proposed scheme was performed over several FVC datasets and the best equal-error rate (EER) obtained for the final bit-string is 1.61%. In addition, extensive analysis was done to justify the non-invertibility and revocability property of the cancellable template.

Original languageEnglish
Pages (from-to)197-208
Number of pages12
JournalPattern Recognition
Volume51
DOIs
Publication statusPublished - 2016 Mar 1

Fingerprint

Principal component analysis

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Wong, Wei Jing ; Teoh, Beng Jin ; Kho, Yau Hee ; Dennis Wong, M. L. / Kernel PCA enabled bit-string representation for minutiae-based cancellable fingerprint template. In: Pattern Recognition. 2016 ; Vol. 51. pp. 197-208.
@article{0bbc00b877df4956add3f4d541b82fd9,
title = "Kernel PCA enabled bit-string representation for minutiae-based cancellable fingerprint template",
abstract = "Minutiae set is one of the prevalent features used to represent a fingerprint. Many minutiae protection schemes have been proposed in recent literature, but only a few have demonstrated successful conversion from minutiae set to fixed-length bit-string. In this paper, we develop a fixed-length binary cancellable fingerprint template generation scheme based on a minutia descriptor known as the multi-line code (MLC). While retaining the core of MLC algorithm, we transform the unordered and variable-size MLC template into an ordered and fixed-length bit-string using kernel principal components analysis (KPCA) and state-of-the-art binarization techniques. The construction of a proper kernel suited for the scenario was validated using Mercer's Theorem. Evaluation of the proposed scheme was performed over several FVC datasets and the best equal-error rate (EER) obtained for the final bit-string is 1.61{\%}. In addition, extensive analysis was done to justify the non-invertibility and revocability property of the cancellable template.",
author = "Wong, {Wei Jing} and Teoh, {Beng Jin} and Kho, {Yau Hee} and {Dennis Wong}, {M. L.}",
year = "2016",
month = "3",
day = "1",
doi = "10.1016/j.patcog.2015.09.032",
language = "English",
volume = "51",
pages = "197--208",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "Elsevier Limited",

}

Kernel PCA enabled bit-string representation for minutiae-based cancellable fingerprint template. / Wong, Wei Jing; Teoh, Beng Jin; Kho, Yau Hee; Dennis Wong, M. L.

In: Pattern Recognition, Vol. 51, 01.03.2016, p. 197-208.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Kernel PCA enabled bit-string representation for minutiae-based cancellable fingerprint template

AU - Wong, Wei Jing

AU - Teoh, Beng Jin

AU - Kho, Yau Hee

AU - Dennis Wong, M. L.

PY - 2016/3/1

Y1 - 2016/3/1

N2 - Minutiae set is one of the prevalent features used to represent a fingerprint. Many minutiae protection schemes have been proposed in recent literature, but only a few have demonstrated successful conversion from minutiae set to fixed-length bit-string. In this paper, we develop a fixed-length binary cancellable fingerprint template generation scheme based on a minutia descriptor known as the multi-line code (MLC). While retaining the core of MLC algorithm, we transform the unordered and variable-size MLC template into an ordered and fixed-length bit-string using kernel principal components analysis (KPCA) and state-of-the-art binarization techniques. The construction of a proper kernel suited for the scenario was validated using Mercer's Theorem. Evaluation of the proposed scheme was performed over several FVC datasets and the best equal-error rate (EER) obtained for the final bit-string is 1.61%. In addition, extensive analysis was done to justify the non-invertibility and revocability property of the cancellable template.

AB - Minutiae set is one of the prevalent features used to represent a fingerprint. Many minutiae protection schemes have been proposed in recent literature, but only a few have demonstrated successful conversion from minutiae set to fixed-length bit-string. In this paper, we develop a fixed-length binary cancellable fingerprint template generation scheme based on a minutia descriptor known as the multi-line code (MLC). While retaining the core of MLC algorithm, we transform the unordered and variable-size MLC template into an ordered and fixed-length bit-string using kernel principal components analysis (KPCA) and state-of-the-art binarization techniques. The construction of a proper kernel suited for the scenario was validated using Mercer's Theorem. Evaluation of the proposed scheme was performed over several FVC datasets and the best equal-error rate (EER) obtained for the final bit-string is 1.61%. In addition, extensive analysis was done to justify the non-invertibility and revocability property of the cancellable template.

UR - http://www.scopus.com/inward/record.url?scp=84955629663&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84955629663&partnerID=8YFLogxK

U2 - 10.1016/j.patcog.2015.09.032

DO - 10.1016/j.patcog.2015.09.032

M3 - Article

VL - 51

SP - 197

EP - 208

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

ER -