Spoofing in 2d face recognition with 3d masks and anti-spoofing with kinect

The problem of detecting face spoofing attacks (presen-tation attacks) has recently gained a well-deserved popu-larity. Mainly focusing on 2D attacks forged by displaying printed photos or replaying recorded videos on mobile de-vices, a significant portion of these studies ground their ar-guments on the flatness of the spoofing material in front of the sensor. In this paper, we inspect the spoofing potential of subject-specific 3D facial masks for 2D face recognition. Additionally, we analyze Local Binary Patterns based coun-termeasures using both color and depth data, obtained by Kinect. For this purpose, we introduce the 3D Mask Attack Database (3DMAD), the first publicly available 3D spoof-ing database, recorded with a low-cost depth camera. Ex-tensive experiments on 3DMAD show that easily attainable facial masks can pose a serious threat to 2D face recog-nition systems and LBP is a powerful weapon to eliminate it. 1