In this paper, we address the problem of FingerCode-based identity matching using encrypted templates. Instead of the classical approach of combining secure signal processing (SSP) tools to mimic the behavior of some wellknown identity matching algorithm, we will investigate the possibility of using a SSP-friendly biometric implementation, i.e., an implementation based on SSP tools. We will propose two alternative strategies for reducing the size of the FingerCode templates, to make them compatible with existing SSP solutions. Experimental results show that feature size reduction has a very limited impact on the accuracy of the biometric system, demonstrating that encrypted domain identity matching can be implemented without sacrificing biometric performance.
Implementing FingerCode-Based Identity Matching in the Encrypted Domain / T. Bianchi, S. Turchi, A. Piva, R. Donida Labati, V. Piuri, F. Scotti - In: Biometric Measurements and Systems for Security and Medical Applications (BIOMS), 2010 IEEE Workshop on[s.l] : IEEE, 2010 Sep. - ISBN 9781424463022. - pp. 15-21 (( Intervento presentato al 1. convegno Biometric Measurements and Systems for Security and Medical Applications tenutosi a Taranto nel 2010 [10.1109/BIOMS.2010.5610445].
Implementing FingerCode-Based Identity Matching in the Encrypted Domain
R. Donida Labati;V. Piuri;F. Scotti
2010
Abstract
In this paper, we address the problem of FingerCode-based identity matching using encrypted templates. Instead of the classical approach of combining secure signal processing (SSP) tools to mimic the behavior of some wellknown identity matching algorithm, we will investigate the possibility of using a SSP-friendly biometric implementation, i.e., an implementation based on SSP tools. We will propose two alternative strategies for reducing the size of the FingerCode templates, to make them compatible with existing SSP solutions. Experimental results show that feature size reduction has a very limited impact on the accuracy of the biometric system, demonstrating that encrypted domain identity matching can be implemented without sacrificing biometric performance.File | Dimensione | Formato | |
---|---|---|---|
bioms2010.pdf
accesso aperto
Tipologia:
Post-print, accepted manuscript ecc. (versione accettata dall'editore)
Dimensione
244.11 kB
Formato
Adobe PDF
|
244.11 kB | Adobe PDF | Visualizza/Apri |
Implementing_FingerCode-based_identity_matching_in_the_encrypted_domain.pdf
accesso riservato
Tipologia:
Publisher's version/PDF
Dimensione
679.02 kB
Formato
Adobe PDF
|
679.02 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.