Browsing NTNU Open by Author "Terhorst, Philipp"

Now showing items 1-3 of 3

    • Analyzing Fairness in Deepfake Detection With Massively Annotated Databases 

      Terhorst, Philipp; Pedersen, Marius; Bylappa Raja, Kiran (Journal article; Peer reviewed, 2024)
      In recent years, image and video manipulations with Deepfake have become a severe concern for security and society. Many detection models and datasets have been proposed to detect Deepfake data reliably. However, there is ...

    • An Attack on Facial Soft-Biometric Privacy Enhancement 

      Osorio-Roig, Daile; Rathgeb, Christian; Drozdowski, Pawel; Terhorst, Philipp; Struc, Vitomir; Busch, Christoph (Peer reviewed; Journal article, 2022)
      In the recent past, different researchers have proposed privacy-enhancing face recognition systems designed to conceal soft-biometric attributes at feature level. These works have reported impressive results, but generally ...

    • Pixel-Level Face Image Quality Assessment for Explainable Face Recognition 

      Terhorst, Philipp; Huber, Marco; Damer, Naser; Kirchbuchner, Florian; Raja, Kiran; Kuijper, Arjan (Peer reviewed; Journal article, 2023)
      In this work, we introduce the concept of pixel-level gface image quality that determines the utility of single pixels in a face image for recognition. We propose a training-free approach to assess the pixel-level qualities ...