Biometrics data analysis and fusion

Abstract

A multimodal biometric system integrates information from multiple biometric sources to compensate for the limitations in performance of each individual biometric system. Although this information integration in a multimodal system can be performed at various levels, fusion at the matching score level is the most common approach due to the ease in accessing and combining the scores generated by different matchers. In this report, we compared four data fusion schemes for combining the matching scores from multiple modalities using the existent data set. Tanh‐estimators method is deployed to unify heterogeneous output from individual biometric in a common domain. Experiments demonstrate the improvement in adopting matching score fusion for multiple biometrics sources. Keywords: Biometric recognition, multimodal biometric systems, matching score fusion, Tanh‐estimators normalization method.