How to handle missing data in robust multi-biometrics verification

Abstract

Conventional multimodal biometrics systems usually do not account for missing modalities that is commonly encountered in real applications. In such cases, robust multimodal biometric verification is needed. In this paper, we present the criteria, fusion method and performance metrics of a robust multimodal biometrics verification system that verifies the client's identity at any condition of data missing. A novel adaptive Support Vector Machine (SVM) classification method is proposed for missing dimensional values. We argue that the usual performance metrics of false accept and false reject rates are insufficient yardsticks for robust verification and propose new metrics against which we benchmark our system.