TU Darmstadt / ULB / TUbiblio

My Eyes Are Up Here: Promoting Focus on Uncovered Regions in Masked Face Recognition

Neto, Pedro C. ; Boutros, Fadi ; Pinto, Joao Ribeiro ; Saffari, Mohsen ; Damer, Naser ; Sequeira, Ana F. ; Cardoso, Jaime S. (2021)
My Eyes Are Up Here: Promoting Focus on Uncovered Regions in Masked Face Recognition.
20th International Conference of the Biometrics Special Interest Group. virtual Conference (15.-17.09.2021)
doi: 10.1109/BIOSIG52210.2021.9548320
Konferenzveröffentlichung, Bibliographie

Kurzbeschreibung (Abstract)

The 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.

Typ des Eintrags: Konferenzveröffentlichung
Erschienen: 2021
Autor(en): Neto, Pedro C. ; Boutros, Fadi ; Pinto, Joao Ribeiro ; Saffari, Mohsen ; Damer, Naser ; Sequeira, Ana F. ; Cardoso, Jaime S.
Art des Eintrags: Bibliographie
Titel: My Eyes Are Up Here: Promoting Focus on Uncovered Regions in Masked Face Recognition
Sprache: Englisch
Publikationsjahr: 27 September 2021
Verlag: IEEE
Buchtitel: BIOSIG 2021: Proceedings of the 20th International Conference of the Biometrics Special Interest Group
Veranstaltungstitel: 20th International Conference of the Biometrics Special Interest Group
Veranstaltungsort: virtual Conference
Veranstaltungsdatum: 15.-17.09.2021
DOI: 10.1109/BIOSIG52210.2021.9548320
Kurzbeschreibung (Abstract):

The 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.

Freie Schlagworte: Biometrics, Face recognition, Deep learning
Fachbereich(e)/-gebiet(e): 20 Fachbereich Informatik
20 Fachbereich Informatik > Graphisch-Interaktive Systeme
Hinterlegungsdatum: 29 Sep 2021 13:12
Letzte Änderung: 29 Sep 2021 13:12
PPN:
Export:
Suche nach Titel in: TUfind oder in Google
Frage zum Eintrag Frage zum Eintrag

Optionen (nur für Redakteure)
Redaktionelle Details anzeigen Redaktionelle Details anzeigen