A Preliminary Study of a New Soft Biometric Finger Recognition for Keystroke Dynamics

International audienceKeystroke dynamics is an interesting biometric modal- ity as a user can be authenticated while typing a passphrase or a password on a keyboard. In order to improve the accuracy of biometric systems, it is possible to exploit some prior information that can be known or extracted from the biometric raw data. This process is known as "soft biometrics". In this paper, we propose a new soft biometric approach for keystroke dynamics con- sisting in extracting from keystroke dynamics templates if the user types with one or two hands. Preliminary experi- mental results show a correct accuracy recognition equal to 80%