no code implementations • 10 Sep 2023 • Usman Muhammad, Mourad Oussalah, Jorma Laaksonen
Conventional feature extraction techniques in the face anti-spoofing domain either analyze the entire video sequence or focus on a specific segment to improve model performance.
no code implementations • 23 Aug 2023 • Usman Muhammad, Mourad Oussalah, Jorma Laaksonen
Inspired by the visual saliency theory, we present a video summarization method for face anti-spoofing detection that aims to enhance the performance and efficiency of deep learning models by leveraging visual saliency.
2 code implementations • 6 Jul 2023 • Usman Muhammad, Md Ziaul Hoque, Mourad Oussalah, Jorma Laaksonen
Face presentation attacks (PA), also known as spoofing attacks, pose a substantial threat to biometric systems that rely on facial recognition systems, such as access control systems, mobile payments, and identity verification systems.
no code implementations • 5 Jan 2023 • Usman Muhammad, Jorma Laaksonen, Djamila Romaissa Beddiar, Mourad Oussalah
The latter combines the predictions from the base models, leveraging their complementary information to better handle unseen target domains and enhance the overall performance.
no code implementations • 28 Aug 2022 • Usman Muhammad, Mourad Oussalah
In particular, the proposed scheme provides a much lower error (from 15. 2% to 6. 7% on CASIA-FASD and 5. 9% to 4. 9% on Replay-Attack) compared to baselines in cross-database scenarios.
no code implementations • 27 Aug 2022 • Usman Muhammad, Mourad Oussalah
To achieve this, we exploit the temporal consistency based on three RGB frames which are acquired at three different times in the video sequence.