AN INTELLIGENT CLASSIFIER FUSION TECHNIQUE FOR IMPROVED MULTIMODAL BIOMETRIC AUTHENTICATION USING MODIFIED DEMPSTER-SHAFER RULE OF COMBINATION

Abstract

Multimodal biometric technology relatively is a technology developed to overcome those limitations imposed by unimodalbiometric systems. The paradigm consolidates evidence from multiple biometric sources offering considerableimprovements in reliability with reasonably overall performance in many applications. Meanwhile, the issue of efficient andeffective information fusion of these evidences obtained from different sources remains an obvious concept that attractsresearch attention. In this research paper, we consider a classical classifier fusion technique, Dempster’s rule of combinationproposed in Dempster-Shafer Theory (DST) of evidence. DST provides useful computational scheme for integratingaccumulative evidences and possesses the potential to update the prior every time a new data is added in the database.However, it has some shortcomings. Dempster Shafer evidence combination has this inability to respond adequately to thefusion of different basic belief assignments (bbas) of evidences, even when the level of conflict between sources is low. Italso has this tendency of completely ignoring plausibility in the measure of its belief. To solve these problems, this paperpresents a modified Dempster’s rule of combination for multimodal biometric authentication which integrates hyperbolictangent (tanh) estimators to overcome the inadequate normalization steps done in the original Dempster’s rule ofcombination. We also adopt a multi-level decision threshold to its measure of belief to model the modified Dempster Shaferrule of combination.Keywords: Information fusion, Multimodal Biometric Authentication, Normalization technique, Tanh Estimators.