TY - JOUR
T1 - Generating fixed-length representation from minutiae using kernel methods for fingerprint authentication
AU - Jin, Zhe
AU - Lim, Meng Hu
AU - Teoh, Andrew Beng Jin
AU - Goi, Bok Min
AU - Tay, Yong Haur
N1 - Funding Information:
This work was supported in part by the National Research Foundation of Korea under Grant 2013006574, in part by the Universiti Tunku Abdul Rahman Research Fund (UTARRF) under Grant IPSR/RMC/UTARRF/2013-C2/G04, in part by the Anhui Provincial Project of Natural Science under Grant KJ2014A095, and in part by the eScience, MOSTI, Malaysia, under Grant 01-02-11-SF0201.
Publisher Copyright:
© 2016 IEEE.
Copyright:
Copyright 2018 Elsevier B.V., All rights reserved.
PY - 2016/10
Y1 - 2016/10
N2 - The ISO/IEC 19794-2-compliant fingerprint minutiae template is an unordered and variable-sized point set data. Such a characteristic leads to a restriction for the applications that can only operate on fixed-length binary data, such as cryptographic applications and certain biometric cryptosystems (e.g., fuzzy commitment). In this paper, we propose a generic point-to-string conversion framework for fingerprint minutia based on kernel learning methods to generate discriminative fixed length binary strings, which enables rapid matching. The proposed framework consists of four stages: 1) minutiae descriptor extraction; 2) a kernel transformation method that is composed of kernel principal component analysis or kernelized locality-sensitive hashing for fixed length vector generation; 3) a dynamic feature binarization; and 4) matching. The promising experimental results on six datasets from fingerprint verification competition (FVC)2002 and FVC2004 justify the feasibility of the proposed framework in terms of matching accuracy, efficiency, and template randomness.
AB - The ISO/IEC 19794-2-compliant fingerprint minutiae template is an unordered and variable-sized point set data. Such a characteristic leads to a restriction for the applications that can only operate on fixed-length binary data, such as cryptographic applications and certain biometric cryptosystems (e.g., fuzzy commitment). In this paper, we propose a generic point-to-string conversion framework for fingerprint minutia based on kernel learning methods to generate discriminative fixed length binary strings, which enables rapid matching. The proposed framework consists of four stages: 1) minutiae descriptor extraction; 2) a kernel transformation method that is composed of kernel principal component analysis or kernelized locality-sensitive hashing for fixed length vector generation; 3) a dynamic feature binarization; and 4) matching. The promising experimental results on six datasets from fingerprint verification competition (FVC)2002 and FVC2004 justify the feasibility of the proposed framework in terms of matching accuracy, efficiency, and template randomness.
KW - Fingerprint
KW - fixed-length representation
KW - kernel methods
KW - randomness of bit-string
UR - http://www.scopus.com/inward/record.url?scp=84988602855&partnerID=8YFLogxK
U2 - 10.1109/TSMC.2015.2499725
DO - 10.1109/TSMC.2015.2499725
M3 - Article
AN - SCOPUS:84988602855
SN - 2168-2216
VL - 46
SP - 1415
EP - 1428
JO - IEEE Transactions on Systems, Man, and Cybernetics: Systems
JF - IEEE Transactions on Systems, Man, and Cybernetics: Systems
IS - 10
ER -