4D Presentation Attack Detection
Team
Martin Thümmel, Sven Sickert
Motivation

The digitalization of organizational processes is progressing fast. At the same time, the need for robust, unsupervised authentication methods is increasing. Typical organizational processes are automated border control, the opening of a bank account, financial transfer, and mobile payments using self-service eGates, kiosks, and smart devices. However, current authentication methods are susceptible to advanced spoofing attacks or identity thefts. In this project we aim to develop more robust representations and methods based on temporal high-resolution 3D sensor data.

Publications
2021
Facial Behavior Analysis using 4D Curvature Statistics for Presentation Attack Detection
Martin Thümmel and Sven Sickert and Joachim Denzler.
IEEE International Workshop on Biometrics and Forensics (IWBF). Pages 1-6. 2021.
[bibtex] [web] [code] [abstract]