Neto, PedroBoutros, FadiPinto, João RibeiroSaffari, MohsenDamer, NaserSequeira, Ana F.Cardoso, Jaime S.Brömme, ArslanBusch, ChristophDamer, NaserDantcheva, AntitzaGomez-Barrero, MartaRaja, KiranRathgeb, ChristianSequeira, AnaUhl, Andreas2021-10-042021-10-042021978-3-88579-709-8https://dl.gi.de/handle/20.500.12116/37465The recent Covid-19 pandemic and the fact that wearing masks in public is now mandatory in several countries, created challenges in the use of face recognition systems (FRS). In this work, we address the challenge of masked face recognition (MFR) and focus on evaluating the verification performance in FRS when verifying masked vs unmasked faces compared to verifying only unmasked faces. We propose a methodology that combines the traditional triplet loss and the mean squared error (MSE) intending to improve the robustness of an MFR system in the masked-unmasked comparison mode. The results obtained by our proposed method show improvements in a detailed step-wise ablation study. The conducted study showed significant performance gains induced by our proposed training paradigm and modified triplet loss on two evaluation databases.enFace recognitionmasked face recognitionCovid-19triplet lossvggface2Text/Conference Paper1617-5468