no code implementations • 5 Mar 2024 • Ahmad Hassanpour, Yasamin Kowsari, Hatef Otroshi Shahreza, Bian Yang, Sebastien Marcel
This paper explores the application of large language models (LLMs), like ChatGPT, for biometric tasks.
no code implementations • 29 Nov 2023 • Pavel Korshunov, Haolin Chen, Philip N. Garner, Sebastien Marcel
From the publicly available speech dataset LibriTTS, we also created a separate database of only audio deepfakes LibriTTS-DF using several latest text to speech methods: YourTTS, Adaspeech, and TorToiSe.
no code implementations • 15 Sep 2023 • Parsa Rahimi, Christophe Ecabert, Sebastien Marcel
Recently, it has been exposed that some modern facial recognition systems could discriminate specific demographic groups and may lead to unfair attention with respect to various facial attributes such as gender and origin.
1 code implementation • 13 Jul 2023 • Anjith George, Sebastien Marcel
Heterogeneous Face Recognition (HFR) aims to match face images across different domains, such as thermal and visible spectra, expanding the applicability of Face Recognition (FR) systems to challenging scenarios.
3 code implementations • 4 Jul 2023 • Anjith George, Christophe Ecabert, Hatef Otroshi Shahreza, Ketan Kotwal, Sebastien Marcel
In this paper, we present EdgeFace, a lightweight and efficient face recognition network inspired by the hybrid architecture of EdgeNeXt.
Ranked #1 on Lightweight Face Recognition on CFP-FP
no code implementations • 29 Jun 2023 • Ketan Kotwal, Sebastien Marcel
The accuracy of finger vein recognition systems gets degraded due to low and uneven contrast between veins and surroundings, often resulting in poor detection of vein patterns.
no code implementations • 19 Jun 2023 • Ketan Kotwal, Sebastien Marcel
While few, existing fairness measures are based on post-decision data (such as verification accuracy) of biometric systems, we discuss how pre-decision data (score distributions) provide useful insights towards demographic fairness.
2 code implementations • 12 Oct 2022 • Anjith George, Amir Mohammadi, Sebastien Marcel
The core idea of the proposed approach is to add a novel neural network block called Prepended Domain Transformer (PDT) in front of a pre-trained face recognition (FR) model to address the domain gap.
no code implementations • 21 Feb 2022 • Anjith George, David Geissbuhler, Sebastien Marcel
Having a lot of sensors increases the cost of the system, and therefore an understanding of the performance of different sensors against a wide variety of attacks is necessary while selecting the modalities.
1 code implementation • CVPR 2021 • Anjith George, Sebastien Marcel
Automatic methods for detecting presentation attacks are essential to ensure the reliable use of facial recognition technology.
1 code implementation • 16 Nov 2020 • Anjith George, Sebastien Marcel
Although various methods have been suggested for detecting such attacks, most of them over-fit the training set and fail in generalizing to unseen attacks and environments.
no code implementations • 21 Sep 2020 • Zohreh Mostaani, Anjith George, Guillaume Heusch, David Geissbuhler, Sebastien Marcel
The High-Quality Wide Multi-Channel Attack database (HQ-WMCA) database extends the previous Wide Multi-Channel Attack database(WMCA), with more channels including color, depth, thermal, infrared (spectra), and short-wave infrared (spectra), and also a wide variety of attacks.
2 code implementations • 22 Jul 2020 • Anjith George, Sebastien Marcel
The proposed system is evaluated on the publicly available WMCA multi-channel face PAD database, which contains a wide variety of 2D and 3D attacks.
Ranked #1 on Face Anti-Spoofing on MLFP
no code implementations • 22 Jul 2020 • Guillaume Heusch, Anjith George, David Geissbuhler, Zohreh Mostaani, Sebastien Marcel
Conducted experiments show superior performance over similar models acting on either color images or on a combination of different modalities (visible, NIR, thermal and depth), as well as on a SVM-based classifier acting on SWIR image differences.
no code implementations • 30 Jun 2020 • Anjith George, Sebastien Marcel
In a typical face recognition pipeline, the task of the face detector is to localize the face region.
Ranked #1 on Face Presentation Attack Detection on WMCA (ACER@0.2BPCER metric)
1 code implementation • IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 2019 • Anjith George, Zohreh Mostaani, David Geissenbuhler, Olegs Nikisins, Andre Anjos, Sebastien Marcel
We also introduce the new Wide Multi-Channel presentation Attack (WMCA) database for face PAD which contains a wide variety of 2D and 3D presentation attacks for both impersonation and obfuscation attacks.
Ranked #2 on Face Presentation Attack Detection on WMCA
6 code implementations • 9 Jul 2019 • Anjith George, Sebastien Marcel
The proposed approach achieves an HTER of 0% in Replay Mobile dataset and an ACER of 0. 42% in Protocol-1 of OULU dataset outperforming state of the art methods.
1 code implementation • 9 Jul 2019 • Olegs Nikisins, Anjith George, Sebastien Marcel
The proposed system is tested on a very recent publicly available multi-channel PAD database with a wide variety of presentation attacks.
1 code implementation • 20 Dec 2018 • Pavel Korshunov, Sebastien Marcel
The best performing method, which is based on visual quality metrics and is often used in presentation attack detection domain, resulted in 8. 97% equal error rate on high quality Deepfakes.