Scale space texture analysis for face anti-spoofing

Abstract

Face spoofing detection (i.e. face anti-spoofing) is emerging as a new research area and has already attracted a good number of works during the past five years. This paper addresses for the first time the key problem of the variation in the input image quality and resolution in face anti-spoofing. In contrast to most existing works aiming at extracting multiscale descriptors from the original face images, we derive a new multiscale space to represent the face images before texture feature extraction. The new multiscale space representation is derived through multiscale filtering. Three multiscale filtering methods are considered including Gaussian scale space, Difference of Gaussian scale space and Multiscale Retinex. Extensive experiments on three challenging and publicly available face anti-spoofing databases demonstrate the effectiveness of our proposed multiscale space representation in improving the performance of face spoofing detection based on gray-scale and color texture descriptors.