Real-Time Face Antispoofing Using Shearlets

Abstract

Face recognition. A promise made to the modern technologists as the ultimate access control or surveillance technology. However, it is still vulnerable to inexpensive spoofing attacks, which pose a threat to security. Basic face spoofing attacks that use photographs and video are still not addressed appropriately, especially in real-time applications, thereby making security in these environments a difficult task to achieve. Although methods have improved over the last decade, a robust solution that can accommodate changing environments is still out of reach. Face spoofing attacks introduce an object into the scene, which presents curvilinear singularities that are not necessarily portrayed in the same way in different lighting conditions. We present a solution that addresses this problem by using a discrete shearlet transform as an alternative descriptor that can differentiate between a real and a fake face without user-cooperation. We have found the approach can successfully detect blurred edges, texture changes and other noise found in various face spoof attacks. Our benchmarks on the publicly available CASIA-FASD, MSU-MFSD, and OULU-NPU data sets, show that our approach portrays good results and improves on the most popular methods found in the field on modest computer hardware, but requires further improvement to beat the current state of the art. The approach also achieves real-time face spoof discrimination, which makes it a practical solution in real-time applications and a viable augmentation to current face recognition methods.