1 code implementation • 26 Apr 2023 • Marco Huber, Anh Thi Luu, Philipp Terhörst, Naser Damer
Explainable Face Recognition is gaining growing attention as the use of the technology is gaining ground in security-critical applications.
2 code implementations • 22 Nov 2022 • Pedro C. Neto, Ana F. Sequeira, Jaime S. Cardoso, Philipp Terhörst
In the context of biometrics, matching confidence refers to the confidence that a given matching decision is correct.
Ranked #1 on Face Recognition on MORPH
no code implementations • 19 Oct 2022 • Marco Huber, Philipp Terhörst, Florian Kirchbuchner, Naser Damer, Arjan Kuijper
The confidence of a decision is often based on the overall performance of the model or on the image quality.
3 code implementations • 11 Aug 2022 • Ying Xu, Philipp Terhörst, Kiran Raja, Marius Pedersen
In this work, we investigate factors causing biased detection in public Deepfake datasets by (a) creating large-scale demographic and non-demographic attribute annotations with 47 different attributes for five popular Deepfake datasets and (b) comprehensively analysing attributes resulting in AI-bias of three state-of-the-art Deepfake detection backbone models on these datasets.
no code implementations • 23 Mar 2022 • Philipp Terhörst, Florian Bierbaum, Marco Huber, Naser Damer, Florian Kirchbuchner, Kiran Raja, Arjan Kuijper
However, previous works followed evaluation settings consisting of older recognition models, limited cross-dataset and cross-model evaluations, and the use of low-scale testing data.
1 code implementation • 26 Nov 2021 • Philipp Terhörst, Malte Ihlefeld, Marco Huber, Naser Damer, Florian Kirchbuchner, Kiran Raja, Arjan Kuijper
These variabilities can be measured in terms of face image quality which is defined over the utility of a sample for recognition.
Ranked #1 on Face Verification on IJB-B
no code implementations • 24 Nov 2021 • Dailé Osorio-Roig, Christian Rathgeb, Pawel Drozdowski, Philipp Terhörst, Vitomir Štruc, Christoph Busch
Future works on privacy-enhancing face recognition are encouraged to include the proposed attack in evaluations on the privacy protection.
1 code implementation • 21 Oct 2021 • Philipp Terhörst, Marco Huber, Naser Damer, Florian Kirchbuchner, Kiran Raja, Arjan Kuijper
To achieve this, a model-specific quality value of the input image is estimated and used to build a sample-specific quality regression model.
1 code implementation • 10 Jun 2021 • Philipp Terhörst, André Boller, Naser Damer, Florian Kirchbuchner, Arjan Kuijper
The implementation is publicly available.
no code implementations • 2 Mar 2021 • Philipp Terhörst, Jan Niklas Kolf, Marco Huber, Florian Kirchbuchner, Naser Damer, Aythami Morales, Julian Fierrez, Arjan Kuijper
However, to enable a trustworthy FR technology, it is essential to know the influence of an extended range of facial attributes on FR beyond demographics.
1 code implementation • 2 Dec 2020 • Philipp Terhörst, Daniel Fährmann, Jan Niklas Kolf, Naser Damer, Florian Kirchbuchner, Arjan Kuijper
In this work, we propose MAADFace, a new face annotations database that is characterized by the large number of its high-quality attribute annotations.
no code implementations • 21 Sep 2020 • Philipp Terhörst, Daniel Fährmann, Naser Damer, Florian Kirchbuchner, Arjan Kuijper
For evaluating the predictability of the attributes, we trained a massive attribute classifier that is additionally able to accurately state its prediction confidence.
1 code implementation • 2 Apr 2020 • Philipp Terhörst, Jan Niklas Kolf, Naser Damer, Florian Kirchbuchner, Arjan Kuijper
Face quality assessment aims at estimating the utility of a face image for the purpose of recognition.
3 code implementations • 20 Mar 2020 • Philipp Terhörst, Jan Niklas Kolf, Naser Damer, Florian Kirchbuchner, Arjan Kuijper
Face image quality is an important factor to enable high performance face recognition systems.
Ranked #1 on Face Quality Assessement on LFW
1 code implementation • 21 Feb 2020 • Philipp Terhörst, Marco Huber, Naser Damer, Florian Kirchbuchner, Arjan Kuijper
Current research on soft-biometrics showed that privacy-sensitive information can be deduced from biometric templates of an individual.
1 code implementation • 10 Feb 2020 • Philipp Terhörst, Jan Niklas Kolf, Naser Damer, Florian Kirchbuchner, Arjan Kuijper
In contrast to previous works, our fair normalization approach enhances the overall performance by up to 53. 2% at false match rate of 0. 001 and up to 82. 9% at a false match rate of 0. 00001.