On-line signature authentication: user adaptive template protection and renewability
Emanuele Maiorana, Patrizio Campisi, Alessandro Neri · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 2008
In this paper an adaptive feature-based approach to on-line signature verification is presented. Cryptographic techniques are employed to protect the extracted templates thus making impossible to derive the original biometric data from the stored information, as well as to generate multiple templates from the same original biometrics. Our approach allows to obtain, together with protection, also template cancelability thus guaranteeing user's privacy. The proposed authentication scheme is able to automatically adjust its parameters to the variability of each user's signature, thus obtaining a user adaptive system with enhanced performances with respect to a nonadaptive one. Experimental results show the effectiveness of our approach. Also the effects on the recognition performances when using the pen inclination features are investigated.