Dempster-Shafer-Based Fusion of Multi-Modal Biometrics for Supporting Identity Verification Effectively and Efficiently

Abstract

The purpose of this paper is to describe a novel fusion algorithm for multi-modal biometric identification. In this paper we describe the fusion of fingerprints and voice. This combination of biometrics is rarely used in verification systems although this biometric pair is simple to use and not too invasive. A framework for the combination of several data fusion algorithms is described. In this paper we use only two types of data fusion techniques, namely weighted sum and fuzzy system. Two independent identity decisions can be thus obtained, and from them two beliefs that the identity is verified can be derived. The two beliefs are combined using Dempster-Shafer's approach to obtain the final decision. The results are reported by ROC curves.

Evaluation of Decision Fusion Methods for Multimodal Biometrics in the Banking Application

“…Singh et al [ 25 ] employed DST to fuse comparison scores of various fingerprint-based verification approaches, including analysis of scores of minutiae, ridges, multi-frequency analysis of prints by the bank of filters, and pores characteristics, in result increasing key performance metrics of this multimodal verification. Cuzzocrea and Mumolo [ 26 ] employed a cascaded approach: fused fingerprints and voice with weighted sum and fuzzy logic, both treated as two decisions that were finally merged applying DST.…”

“…The problems were addressed in numerous works and are widely known in the literature [ 34 ]. The aspect of imprecision was often considered in applications such as biometrics [ 24 , 25 , 26 , 36 ], and some examples were provided in Section 3 .…”