FRANÇAIS
A showcase of ÉTS researchers’ publications and other contributions
SEARCH

A dual-staged classification-selection approach for automated update of biometric templates

Downloads

Downloads per month over past year

Rattani, Ajita and Marcialis, Gian Luca and Granger, Éric and Roli, Fabio. 2012. « A dual-staged classification-selection approach for automated update of biometric templates ». In 21st International Conference on Pattern Recognition (ICPR) (Tsukuba, Japan, Nov. 11-15, 2012), pp. 2972-2975. Piscataway, NJ : Institute of Electrical and Electronics Engineers Inc..
Compte des citations dans Scopus : 9.

[img]
Preview
PDF
Granger E. 2012 5085 A dual-staged classification-selection approach for automated update of biometric templates.pdf

Download (310kB) | Preview

Abstract

In the emerging field of adaptive biometrics, systems aim to adapt enrolled templates to variations in samples observed during operations. However, despite numerous advantages, few commercial vendors have adopted auto-update procedures in their products. This is due to limitations associated with existing adaptation schemes. This paper proposes a dual-staged template adaptation scheme that allows to capture ‘informative’ operational samples with significant variations but without increasing the vulnerability to impostor intrusion. This is achieved through a two staged classification-selection approach driven by the harmonic function and risk minimization technique, over a graph based representation of (enrolment and operational) samples. Experimental results on the DIEE fingerprint data set, explicitly collected for evaluating adaptive biometric systems, demonstrate that the proposed scheme results in 67% reduction in error over the baseline system (without adaptation), outperforming state-of-the-art methods.

Item Type: Conference proceeding
Professor:
Professor
Granger, Éric
Affiliation: Génie de la production automatisée
Date Deposited: 24 Jul 2013 20:43
Last Modified: 29 Jan 2016 01:16
URI: http://espace2.etsmtl.ca/id/eprint/5085

Actions (login required)

View Item View Item