Fuzzy logic decision fusion in a multimodal biometric system

Abstract

This paper presents a multi-biometric verification system that combines speaker verification, fingerprint verification with face identification. Their respective equal error rates (EER) are 4.3%, 5.1% and the range of (5.1% to 11.5%) for matched conditions in facial image capture. Fusion of the three by majority voting gave a relative improvement of 48% over speaker verification (i.e. the best-performing biometric). Fusion by weighted average scores produced a further relative improvement of 52%.We propose the use of fuzzy logic decision fusion, in order to account for external conditions that affect verification performance. Examples include recording conditions of utterances for speaker verification, lighting and facial expressions in face identification and finger placement and pressure for fingerprint verification. The fuzzy logic framework incorporates some external factors relating to face and fingerprint verification and achieved an additional improvement of 19%.

Decision Fusion Using Fuzzy Logic Type 1 for Two Aviation Scenarios

“…Application of fuzzy logic in decision fusion for a multimodal biometric system has been considered in [10], and for the classification of urban remote sensing images has been treated in [11]. Here, we consider aviation scenarios.…”

EVI: Multilingual Spoken Dialogue Tasks and Dataset for Knowledge-Based Enrolment, Verification, and Identification

“…Furthermore, enrolment is a particular case of the slot-filling dialogue task (Young, 2002;Bellegarda, 2014); and identification is related to information retrieval and shares challenges with entity linking (Ling et al, 2015;Hoffart et al, 2014;McNamee and Dang, 2009). We extend fuzzy logic methods from information retrieval (Radecki, 1979;Zadrożny and Nowacka, 2009;Salton et al, 1983) and from multi-modal verification (Lau et al, 2004;Conti et al, 2007;Azzini et al, 2007) to the context of spoken dialogues.…”