Multi-Modal Fingerprint Presentation Attack Detection: Analysing the Surface and the Inside

The deployment of biometric recognition systems has seen a considerable increase over the last decade, in particular for fingerprint based systems. To tackle the security issues derived from presentation attacks launched on the biometric capture device, automatic presentation attack detection (PAD) methods have been proposed. In spite of their high detection rates on the LivDet databases, the vast majority of the methods rely on the samples provided by traditional capture devices, which may fail to detect more sophisticated presentation attack instrument (PAI) species. In this paper, we propose a multi-modal fingerprint PAD which relies on an analysis of: i) the surface of the finger within the short wave infrared (SWIR) spectrum, and ii) the inside of the finger thanks to the laser speckle contrast imaging (LSCI) technology. On the experimental evaluation over a database comprising more than 4700 samples and 35 PAI species, and including unknown attacks to model a realistic scenario, a Detection Equal Error Rate (D-EER) of 0.5% has been achieved. Moreover, for a BPCER ≤ 0.1% (i.e., highly convenient system), the APCER remains around 3%.

1. Introduction

The advantages offered by biometric systems in contrast to traditional PIN or token based authentication systems are well known [15]: a stronger link between the subject and the physical authentication factor (e.g. a passport), or no need to carry items, which can be lost, or to struggle to remember complex passwords. These facts have allowed a wide deployment of biometric systems in high security environments (e.g., border crossing) and everyday applications (e.g., smartphone unlocking).