Revisiting feature level and score level fusion techniques in multimodal biometrics system

Abstract

The primary application of biometric technology is to analyze human characteristics for security purpose as security issues have been the focused interest in recent years. A survey of different fusion techniques in multimodal biometrics is made. This paper also attempts to identify some of the challenges and issues that confront research in multimodal biometrics. Keywords-Multi modal; feature level fusion; score level fusionI.

Integrating Fusion levels for Biometric Authentication System

“…A biometric system that fuses the information from multiple traits is known as multimodal biometric system. These systems are more reliable due to the presence of multiple, independent biometrics [2]. Remarkable improvement of the biometric system accuracy can also be further achieved by integrating the fusion level techniques taking the advantage of both the fusion techniques.…”

“…FRR is the percentage of authorized individuals rejected by the system and FAR is the percentage of unauthorized persons accepted by the system. The point where FRR and FAR have the same value is called ERR [2]. The limitations of unimodal biometric systems motivated the inclusion of multiple sources of information for establishing identity.…”