Multi-modal biometrics authentication using on-line signature and voice pitch

We have studied the on-line signature verification method based on DWT sub-band decomposition. High verification rate was achieved even when forgers traced genuine signatures. In this paper, we propose a multi-modal biometrics authentication system of pitch verification and on-line signature verification in order to obtain higher verification rate. We use a self-correlation function for extraction of a voice pitch and verify by a standardized variable. Moreover, we try fusion methods of abstract level and score level. In order to confirm effectiveness of our proposed verification system, we carried out experiments of the verification.