On the Generalisation Capabilities of Fisher Vector based Face Presentation Attack Detection

TL;DR

This paper introduces a Fisher Vector based feature representation for face presentation attack detection, improving detection of unknown attacks and achieving state-of-the-art results in challenging scenarios.

Contribution

The work proposes a novel Fisher Vector feature space from Binarised Statistical Image Features to enhance unknown attack detection in face PAD.

Findings

Achieves BPCER100 under 17% with AUC over 98% on unknown attacks.

Outperforms existing methods in cross-dataset scenarios.

Uses limited parameters to match deep learning approaches.

Abstract

In the last decades, the broad development experienced by biometric systems has unveiled several threats which may decrease their trustworthiness. Those are attack presentations which can be easily carried out by a non-authorised subject to gain access to the biometric system. In order to mitigate those security concerns, most face Presentation Attack Detection techniques have reported a good detection performance when they are evaluated on known Presentation Attack Instruments (PAI) and acquisition conditions, in contrast to more challenging scenarios where unknown attacks are included in the test set. For those more realistic scenarios, the existing algorithms face difficulties to detect unknown PAI species in many cases. In this work, we use a new feature space based on Fisher Vectors, computed from compact Binarised Statistical Image Features histograms, which allow discovering semantic feature subsets from known samples in order to enhance the detection of unknown attacks. This new representation, evaluated for challenging unknown attacks taken from freely available facial databases, shows promising results: a BPCER100 under 17% together with an AUC over 98% can be achieved in the presence of unknown attacks. In addition, by training a limited number of parameters, our method is able to achieve state-of-the-art deep learning-based approaches for cross-dataset scenarios.