Facial Behavior Analysis using 4D Curvature Statistics for Presentation Attack Detection

TL;DR

This paper introduces a novel 4D curvature-based facial behavior analysis method for detecting presentation attacks, effectively identifying various biometric spoofing techniques using only genuine face data for training.

Contribution

The study presents a new 4D curvature statistics approach for presentation attack detection that operates in an unsupervised manner, focusing on facial behavior plausibility.

Findings

Achieved 11% APCER and 6% BPCER error rates.

Successfully detected elastic masks, bent photos, and replay attacks.

Utilized a challenging 109-scan database with diverse attack types.

Abstract

The human face has a high potential for biometric identification due to its many individual traits. At the same time, such identification is vulnerable to biometric copies. These presentation attacks pose a great challenge in unsupervised authentication settings. As a countermeasure, we propose a method that automatically analyzes the plausibility of facial behavior based on a sequence of 3D face scans. A compact feature representation measures facial behavior using the temporal curvature change. Finally, we train our method only on genuine faces in an anomaly detection scenario. Our method can detect presentation attacks using elastic 3D masks, bent photographs with eye holes, and monitor replay-attacks. For evaluation, we recorded a challenging database containing such cases using a high-quality 3D sensor. It features 109 4D face scans including eleven different types of presentation attacks. We achieve error rates of 11% and 6% for APCER and BPCER, respectively.