Construct a new fixed-length binary fingerprint representation using Kernelized Locality-Sensitive Hashing

Zhe Jin; Andrew Beng Jin Teoh

doi:10.1109/ICIEA.2015.7334128

Construct a new fixed-length binary fingerprint representation using Kernelized Locality-Sensitive Hashing

Zhe Jin
, Andrew Beng Jin Teoh

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

2 Citations (Scopus)

Abstract

ISO/IEC 19794-2 compliant fingerprint minutiae template is an unordered and variable-size point set data. Such characteristic leads to restriction to the applications that can only operate on the ordered fixed-length bit-string, such as cryptographic protocols and biometric cryptosystem scheme like fuzzy commitment and fuzzy extractor operating in hamming domain. In this paper, we propose a discriminative fixed-length binary representation converted from fingerprint minutia based on Kernelized Locality-Sensitive Hashing (KLSH), which enables speedy matching. The proposed method includes four steps: minutiae descriptor extraction; Kernelized Locality-Sensitive Hashing for fixed length vector generation; dynamic feature binarization and matching. Experimental results on FVC2002 databases justify the feasibility of the proposed template in terms of matching accuracy and template randomness.

Original language	English
Title of host publication	Proceedings of the 2015 10th IEEE Conference on Industrial Electronics and Applications, ICIEA 2015
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	296-301
Number of pages	6
ISBN (Electronic)	9781467373173
DOIs	https://doi.org/10.1109/ICIEA.2015.7334128
Publication status	Published - 20 Nov 2015
Externally published	Yes
Event	IEEE Conference on Industrial Electronics and Applications 2015 - Auckland, New Zealand Duration: 15 Jun 2015 → 17 Jun 2015 Conference number: 10th http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1001289 (Proceedings)

Conference

Conference	IEEE Conference on Industrial Electronics and Applications 2015
Abbreviated title	ICIEA 2015
Country/Territory	New Zealand
City	Auckland
Period	15/06/15 → 17/06/15
Other	Conference Pub Title (from RM records)= 2015 10th IEEE Conference on Industrial Electronics and Applications (ICIEA 2015)
Internet address	http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1001289 (Proceedings)

Keywords

Fingerprint minutiae
Fixed-length Representation
Kernerlized Locality-sensitive Hashing
Template Randomness

Access to Document

10.1109/ICIEA.2015.7334128

Cite this

@inproceedings{1b39b618822b45cca101dad9bf8490df,

title = "Construct a new fixed-length binary fingerprint representation using Kernelized Locality-Sensitive Hashing",

abstract = "ISO/IEC 19794-2 compliant fingerprint minutiae template is an unordered and variable-size point set data. Such characteristic leads to restriction to the applications that can only operate on the ordered fixed-length bit-string, such as cryptographic protocols and biometric cryptosystem scheme like fuzzy commitment and fuzzy extractor operating in hamming domain. In this paper, we propose a discriminative fixed-length binary representation converted from fingerprint minutia based on Kernelized Locality-Sensitive Hashing (KLSH), which enables speedy matching. The proposed method includes four steps: minutiae descriptor extraction; Kernelized Locality-Sensitive Hashing for fixed length vector generation; dynamic feature binarization and matching. Experimental results on FVC2002 databases justify the feasibility of the proposed template in terms of matching accuracy and template randomness.",

keywords = "Fingerprint minutiae, Fixed-length Representation, Kernerlized Locality-sensitive Hashing, Template Randomness",

author = "Zhe Jin and Teoh, \{Andrew Beng Jin\}",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE. Copyright: Copyright 2017 Elsevier B.V., All rights reserved.; IEEE Conference on Industrial Electronics and Applications 2015, ICIEA 2015 ; Conference date: 15-06-2015 Through 17-06-2015",

year = "2015",

month = nov,

day = "20",

doi = "10.1109/ICIEA.2015.7334128",

language = "English",

pages = "296--301",

booktitle = "Proceedings of the 2015 10th IEEE Conference on Industrial Electronics and Applications, ICIEA 2015",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States of America",

url = "http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1001289",

}

Jin, Z & Teoh, ABJ 2015, Construct a new fixed-length binary fingerprint representation using Kernelized Locality-Sensitive Hashing. in Proceedings of the 2015 10th IEEE Conference on Industrial Electronics and Applications, ICIEA 2015. IEEE, Institute of Electrical and Electronics Engineers, pp. 296-301, IEEE Conference on Industrial Electronics and Applications 2015, Auckland, New Zealand, 15/06/15. https://doi.org/10.1109/ICIEA.2015.7334128

Construct a new fixed-length binary fingerprint representation using Kernelized Locality-Sensitive Hashing. / Jin, Zhe; Teoh, Andrew Beng Jin.
Proceedings of the 2015 10th IEEE Conference on Industrial Electronics and Applications, ICIEA 2015. IEEE, Institute of Electrical and Electronics Engineers, 2015. p. 296-301.

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

TY - GEN

T1 - Construct a new fixed-length binary fingerprint representation using Kernelized Locality-Sensitive Hashing

AU - Jin, Zhe

AU - Teoh, Andrew Beng Jin

N1 - Conference code: 10th

PY - 2015/11/20

Y1 - 2015/11/20

N2 - ISO/IEC 19794-2 compliant fingerprint minutiae template is an unordered and variable-size point set data. Such characteristic leads to restriction to the applications that can only operate on the ordered fixed-length bit-string, such as cryptographic protocols and biometric cryptosystem scheme like fuzzy commitment and fuzzy extractor operating in hamming domain. In this paper, we propose a discriminative fixed-length binary representation converted from fingerprint minutia based on Kernelized Locality-Sensitive Hashing (KLSH), which enables speedy matching. The proposed method includes four steps: minutiae descriptor extraction; Kernelized Locality-Sensitive Hashing for fixed length vector generation; dynamic feature binarization and matching. Experimental results on FVC2002 databases justify the feasibility of the proposed template in terms of matching accuracy and template randomness.

AB - ISO/IEC 19794-2 compliant fingerprint minutiae template is an unordered and variable-size point set data. Such characteristic leads to restriction to the applications that can only operate on the ordered fixed-length bit-string, such as cryptographic protocols and biometric cryptosystem scheme like fuzzy commitment and fuzzy extractor operating in hamming domain. In this paper, we propose a discriminative fixed-length binary representation converted from fingerprint minutia based on Kernelized Locality-Sensitive Hashing (KLSH), which enables speedy matching. The proposed method includes four steps: minutiae descriptor extraction; Kernelized Locality-Sensitive Hashing for fixed length vector generation; dynamic feature binarization and matching. Experimental results on FVC2002 databases justify the feasibility of the proposed template in terms of matching accuracy and template randomness.

KW - Fingerprint minutiae

KW - Fixed-length Representation

KW - Kernerlized Locality-sensitive Hashing

KW - Template Randomness

UR - https://www.scopus.com/pages/publications/84960918867

U2 - 10.1109/ICIEA.2015.7334128

DO - 10.1109/ICIEA.2015.7334128

M3 - Conference Paper

AN - SCOPUS:84960918867

SP - 296

EP - 301

BT - Proceedings of the 2015 10th IEEE Conference on Industrial Electronics and Applications, ICIEA 2015

PB - IEEE, Institute of Electrical and Electronics Engineers

T2 - IEEE Conference on Industrial Electronics and Applications 2015

Y2 - 15 June 2015 through 17 June 2015

ER -

Construct a new fixed-length binary fingerprint representation using Kernelized Locality-Sensitive Hashing

Abstract

Conference

Keywords

Access to Document

Other files and links

Cite this