Presentation attack detection algorithm for face and iris biometrics

Abstract

Biometric systems are vulnerable to the diverse attacks that emerged as a challenge to assure the reliability in adopting these systems in real-life scenario. In this work, we propose a novel solution to detect a presentation attack based on exploring both statistical and Cepstral features. The proposed Presentation Attack Detection (PAD) algorithm will extract the statistical features that can capture the micro-texture variation using Binarized Statistical Image Features (BSIF) and Cepstral features that can reflect the micro changes in frequency using 2D Cepstrum analysis. We then fuse these features to form a single feature vector before making a decision on whether a capture attempt is a normal presentation or an artefact presentation using linear Support Vector Machine (SVM). Extensive experiments carried out on a publicly available face and iris spoof database show the efficacy of the proposed PAD algorithm with an Average Classification Error Rate (ACER) = 10.21% on face and ACER = 0% on the iris biometrics.