Fusion in fingerprint authentication: two finger types vs. two scanner types

Authors:
Davrondzhon Gafurov;Christoph Busch;Patrick Bours;Bian Yang
Affiliations:
Gjøvik University College, Gjøvik, Norway;Gjøvik University College, Gjøvik, Norway;Gjøvik University College, Gjøvik, Norway;Norwegian Information Security Lab (NISLab), Gjøvik, Norway
Venue:
Proceedings of the 2011 ACM Symposium on Applied Computing
Year:
2011

Citing 6
Cited 0

Fingerprint verification by fusion of optical and capacitive sensors

Pattern Recognition Letters
Handbook of Fingerprint Recognition

Handbook of Fingerprint Recognition
GUC100 Multi-scanner Fingerprint Database for In-House (Semi-public) Performance and Interoperability Evaluation

ICCSA '10 Proceedings of the 2010 International Conference on Computational Science and Its Applications
GUC100 multisensor fingerprint database for in-house (semipublic) performance test

EURASIP Journal on Information Security
Combining multiple matchers for fingerprint verification: a case study in FVC2004

ICIAP'05 Proceedings of the 13th international conference on Image Analysis and Processing
How do correlation and variance of base-experts affect fusion in biometric authentication tasks?

IEEE Transactions on Signal Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents our study on fingerprint fusion in particular in three scenario sets: a) two fingers captured by the same scanner; b) the same finger captured by two different scanners; and c) two fingers both captured by two different scanners. As a test data set we use GUC100 multi-scanner fingerprint database which contains fingerprint images of all ten fingers from 100 subjects using a number of different fingerprint scanners. In total 780 fusion scenarios are studied. Our analysis indicate that score level fusion using average rule provides improvement in all scenarios. The fusion of the same fingers from different scanners appears to provide more performance improvement compared to the fusion of different fingers from the same scanner. Furthermore, we also reveal that fusion of different fingers both collected by different scanners are the best. Interestingly, results suggest that for fusion differences in scanner type are more valuable than differences in finger type.