Hybrid Template Update System for Unimodal Biometric Systems

TL;DR

This paper introduces a hybrid template update system for unimodal biometric authentication that uses multiple sub-references to improve self-update accuracy, validated on keystroke-dynamics datasets.

Contribution

A novel hybrid approach employing multiple sub-references to enhance template update performance in biometric systems.

Findings

Improved accuracy in keystroke-dynamics authentication over existing methods.

Reduced drift caused by impostor samples and slow adaptation to genuine changes.

Validated on two state-of-the-art datasets with positive results.

Abstract

Semi-supervised template update systems allow to automatically take into account the intra-class variability of the biometric data over time. Such systems can be inefficient by including too many impostor's samples or skipping too many genuine's samples. In the first case, the biometric reference drifts from the real biometric data and attracts more often impostors. In the second case, the biometric reference does not evolve quickly enough and also progressively drifts from the real biometric data. We propose a hybrid system using several biometric sub-references in order to increase per- formance of self-update systems by reducing the previously cited errors. The proposition is validated for a keystroke- dynamics authentication system (this modality suffers of high variability over time) on two consequent datasets from the state of the art.