Fusion of Palmprint and Speech Features for a Secure Multimodal Biometric System

Abstract

This paper proposes, multimodal biometric system for identify verification using two traits, i.e. palmprint and speech signal. The proposed system is designed for applications where the training data contains a palmprint and speech signal. Integrating the palmprint and speech features increases robustness of person authentication. The final decision is made by fusion at matching score level architecture in which feature vectors are created independently for query measures and are then compared to the enrolment templates, which are stored during database preparation. Multimodal system is developed through fusion of palmprint verification and speaker verification. The multimedia system has been designed at multi-classifier and multimodal level. At multi-classifier level, multiple algorithms are combined for better results. At first experimental individual systems were developed and tested for FAR, FRR and accuracy. In the next experiment multiple-classifiers are combined at matching score level for palmprint and speech signal. In the last experiment the two traits are combined at matching score level using sum of score technique.