A countermeasure against face-spoofing attacks using an interaction video framework

With an increase in acceptance of face recognition systems, the desire for accurate biometric authentication — face recognition, has increased. Nowadays, the fundamental limitations of existing systems are, the vulnerabilities of false verification via a picture or simple video of a person. In this paper, it is inspired by how humans can perform reliable spoofing detection only based on the available scene and context information. We propose our framework in a combination of interaction model and Moire pattern analysis to make sure that a user is a real person. It is different from some systems that use hardware-based liveness detection. We focus on the software-based approaches, in particular, the necessary algorithms that allow for a liveness detection in real-time. Our experiments results show excellent performance to the state of the art.