Is Warping-based Cancellable Biometrics (still) Sensible for Face Recognition?

Abstract

We conduct an ISO/IEC Standards 24745 and 30136 compliant assessment of block-based warping sample transformation techniques aiming for template protection. Particular focus is laid on the results' evaluation considering the evolution of face recognition technology ranging from more “historic” hand-crafted features to state-of-the-art deep-learning (DL) based schemes. It turns out that the high robustness of todays face recognition technology can handle geometrical distortions introduced by warping as another form of variability like pose, illumination, and expression variations, thereby disabling the intended protection functionality of warping. Therefore, block-based warping sample transformation must not be used as template protection technique for todays state-of-the-art face recognition schemes, while some settings could be identified providing template protection to some extent for less recent face recognition technology.