SUNRISE: Improving 3D mask Face Anti-spoofing for Short Videos using Pre-emptive Split and Merge

Abstract

In the current digital world, face analytic systems become an integral part of daily life. However, todays cutting-edge technology and readily available social media information make these systems vulnerable through face spoofing attacks. These attacks can be mitigated using remote Photoplethysmography (rPPG), which remotely detects cardiovascular signals. Unfortunately, the illumination variation and face deformations can easily corrupt the pulse signals and thereby degrade the performance of rPPG-based anti-spoofing methods, even when longer-duration face videos are employed. This paper proposes a face anti-spoofing method <b>SUNRISE</b>, that is, <b>S</b>hort videos <b>U</b>si<b>N</b>g p<b>R</b>e-empt<b>I</b>ve <b>S</b>plit and m<b>E</b>rge. It is an rPPG-based face anti-spoofing for short duration videos wherein facial deformations are removed by introducing the split and merge mechanism. It splits the video into several clips, provides low importance to the clips containing facial deformations, and eventually merges the results using quality-based fusion. The efficacy of existing rPPG-based methods is limited because they employed high dimensional features for training using the limited training data. We mitigate this limitation by utilizing the statistical features of clips. The experimental results on publicly available datasets reveal that the proposed method exhibits significantly better performance than the well-known existing methods for a short time duration IEEE