Discriminative multimodal biometric authentication based on quality measures

Abstract

A novel score-level fusion strategy based on quality measures for multimodal biometric authentication is presented. In the proposed method, the fusion function is adapted every time an authentication claim is performed based on the estimated quality of the sensed biometric signals at this time. Experimental results combining written signatures and quality-labelled fingerprints are reported. The proposed scheme is shown to outperform significantly the fusion approach without considering quality signals. In particular, a relative improvement of approximately 20% is obtained on the publicly available MCYT bimodal database.

Incorporating Image Quality in Multi-algorithm Fingerprint Verification

“…These two matchers provide complementary information commonly exploited by score-level fusion [7,8]. Finally, we incorporate the idea of quality-based score fusion [9] into this multiple algorithm approach. In particular, an adaptive score-level fusion technique based on quality indices computed in the spatial frequency domain is presented and evaluated.…”

Impact of time variability in off-line writer identification and verification

“…drop encountered with increased time spans between reference and test, e.g., using quality-activated template update techniques [21], or quality-based information fusion [22].…”

Towards Predicting Good Users for Biometric Recognition Based on Keystroke Dynamics

“…Quality of biometric samples has become an important concern for the biometric community [7] [11]. It is well known that the degradation of quality strongly affects the performance of biometric recognition systems and dealing with such degradation is still an open challenge in many biometric traits.…”