Smartphone Multi-modal Biometric Presentation Attack Detection

Abstract

AbstractBiometric verification is widely employed on smartphones for various applications, including financial transactions. In this work, we present a new multi-modal biometric dataset (face, voice, and periocular) acquired using a smartphone. The new dataset consists of 150 subjects captured in six different sessions reflecting real-life scenarios of smartphone authentication. A unique feature of this dataset is that it is collected in four different geographic locations representing a diverse population and ethnicity. Additionally, we also present a multi-modal presentation attack dataset using low-cost presentation attack Instruments such as print and electronic display attacks. The novel acquisition protocols and the diversity of the data subjects collected from different geographic locations will allow the development of novel algorithms for either uni-modal or multi-modal biometrics. Further, we also report results obtained on the newly collected dataset after conducting performance evaluation experiments using a set of baseline verification and presentation attack detection algorithms that will be described in further detail.