On the Use of Statistical Considerations in Multi-Modal Identity Verification System Design

Abstract

In this chapter, we would like to show two of the possibilities of statistical analysis in the design process of a multi-modal identity verification system. The multi-modal identity verification system under consideration is built of 3 modalities in parallel, each one delivering as output a scalar number, called score, stating how well the claimed identity is verified. A decision fusion module receiving as input the 3 scores has to take a binary decision: accept or reject the claimed identity. We have solved this fusion problem using parametric and non-parametric classifiers. There are two trivial steps in the design process of such a multi-modal identity verification system in which statistical analysis can be useful.