Design of alignment-free cancelable fingerprint templates via curtailed circular convolution

Fraudulent use of stolen fingerprint data and privacy invasion by tracking individuals unlawfully with shared or stolen fingerprint data justify the significance of fingerprint template protection. With no a priori fingerprint image registration, alignment-free cancelable fingerprint templates do no...

Full description

Saved in:
Bibliographic Details
Published in:Pattern recognition 2014-03, Vol.47 (3), p.1321-1329
Main Authors: Wang, Song, Hu, Jiankun
Format: Article
Language:English
Subjects:
Alignment
Alignment-free
Applied sciences
Cancelable templates
Circular convolution
Convolution
Exact sciences and technology
Fingerprints
Image processing
Information, signal and communications theory
Mathematical analysis
One-way transform
Pattern recognition
Security
Signal processing
Strings
Telecommunications and information theory
Tracking
Vectors (mathematics)
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Fraudulent use of stolen fingerprint data and privacy invasion by tracking individuals unlawfully with shared or stolen fingerprint data justify the significance of fingerprint template protection. With no a priori fingerprint image registration, alignment-free cancelable fingerprint templates do not suffer from inaccurate singular point detection. In this paper, we propose an effective alignment-free method for constructing cancelable fingerprint templates via curtailed circular convolution. The proposed method features an efficient one-way transform, which protects the input binary string such that it cannot be retrieved from the length-reduced, convolved output vector. The transformed template fulfills the requirements of non-invertibility, revocability and diversity for cancelable fingerprint templates. Evaluation of the proposed scheme over FVC2002 DB1, DB2 and DB3 shows that the new method demonstrates satisfactory performance compared to the existing alignment-free cancelable template schemes. •Alignment-free cancelable fingerprint templates.•Non-invertible transform via curtailed circular convolution.•Satisfactory matching performance with low equal error rate (EER).•Generated cancelable templates have the properties of non-invertibility, revocability and diversity.•Non-disclosure of original fingerprint data.
ISSN:0031-3203
1873-5142
DOI:10.1016/j.patcog.2013.10.003