A Novel Approach to Improve the Biometric Security using Liveness Detection

Abstract

A biometric system automatically authenticate individuals based on their physical and behavioral features like face, iris retina, ear, voice, signature keystroke dynamics etc. A biometric system which uses only a single trait for recognition is known as unimodal system. In Unimodal biometric system contains some limitation such as high error rate, non-universality, noise in sensed data, and spoof attacks etc. These problems could be overcome by multimodal approaches which combine more than one trait of user for authentication. The main purpose of using liveness detection with multimodal biometric is that we can use this approach in highly secured application such as defense, labs, pharmacies and bank applications. So in this paper liveness detection technique is used with multimodal approach. Initially, it checks the liveness of the person. If the person is found alive, only then the further calculations are performed. The main purpose of the purposed scheme is to reduce the FAR (false acceptance rate), FRR (false reject rate) and provide protection against spoof attacks. Proposed scheme was implemented using MUBI (Multimodal Biometrics Integration) software.