Decision fusion comparison for a biometric verification system using face and speech

This paper presents several fusion decision techniques comparison for a bimodal biometric verification system that makes use of face images and speech utterances. The system is essentially constructed by a face expert, a speech expert and a fusion decision module. Each individual expert has been optimised to operate in automatic mode and designed for security access application. Fusion decision schemes considered are the voting technique, ordinary and modified k-Nearest Neighborhood classifier and linear Support Vector Machine. The aim is to obtain the optimum fusion module from amongst these five techniques best suited to the target application.