Organizer: European Association for Biometrics (EAB)
This lunch talk is part of the EAB virtual events series on Demographic Fairness in Biometric Systems.
See March 15, 2020 for a full description of the events series.
Attendance is free of charge, but registration is required.
Registered participants will receive dial-in credentials on the morning of the event.
Speakers: Philipp Terhörst
Deeply-learned face representations enable the success of current face recognition systems. Despite the ability of these representations to encode the identity of an individual, recent works have shown that more information is stored within, such as demographics, image characteristics, and social traits. This talk will show that many more soft-biometric attributes are embedding in face templates and that these attributes often have a strong correlation on the face verification performance.
Curriculum vitæ
Philipp Terhörst completed his studies in physics at the Technical University of Darmstadt in 2017. Since then, he has been working in the Smart Living & Biometric Technologies department at the Fraunhofer Institute for Computer Graphics Research (IGD) as a researcher. His research interest includes research at machine learning and biometric solutions focusing on quality assessment, privacy-enhancement, and bias-mitigation in face recognition. He is author of several publications in conferences and journals such as CVPR and IEEE Access and is regularly serving as a reviewer (e.g. for TPAMI, TIP, PR, BTAS, ICB). For his scientific work, he received several awards such as the EAB Biometrics Industry Award 2020 from the European Association for Biometrics for his dissertation or the IJCB 2020 Qualcomm PC Chairs Choice Best Student Paper Award. Moreover, he was involved in the Software Campus program, a management program of the Federal Ministry of Education and Research (BMBF).
