TU Darmstadt / ULB / TUbiblio

Self-restrained triplet loss for accurate masked face recognition

Boutros, Fadi ; Damer, Naser ; Kirchbuchner, Florian ; Kuijper, Arjan (2022)
Self-restrained triplet loss for accurate masked face recognition.
In: Pattern Recognition, 124
doi: 10.1016/j.patcog.2021.108473
Artikel, Bibliographie

Kurzbeschreibung (Abstract)

Using the face as a biometric identity trait is motivated by the contactless nature of the capture process and the high accuracy of the recognition algorithms. After the current COVID-19 pandemic, wearing a face mask has been imposed in public places to keep the pandemic under control. However, face occlusion due to wearing a mask presents an emerging challenge for face recognition systems. In this paper, we present a solution to improve masked face recognition performance. Specifically, we propose the Embedding Unmasking Model (EUM) operated on top of existing face recognition models. We also propose a novel loss function, the Self-restrained Triplet (SRT), which enabled the EUM to produce embeddings similar to these of unmasked faces of the same identities. The achieved evaluation results on three face recognition models, two real masked datasets, and two synthetically generated masked face datasets proved that our proposed approach significantly improves the performance in most experimental settings.

Typ des Eintrags: Artikel
Erschienen: 2022
Autor(en): Boutros, Fadi ; Damer, Naser ; Kirchbuchner, Florian ; Kuijper, Arjan
Art des Eintrags: Bibliographie
Titel: Self-restrained triplet loss for accurate masked face recognition
Sprache: Englisch
Publikationsjahr: April 2022
Verlag: Elsevier
Titel der Zeitschrift, Zeitung oder Schriftenreihe: Pattern Recognition
Jahrgang/Volume einer Zeitschrift: 124
DOI: 10.1016/j.patcog.2021.108473
Kurzbeschreibung (Abstract):

Using the face as a biometric identity trait is motivated by the contactless nature of the capture process and the high accuracy of the recognition algorithms. After the current COVID-19 pandemic, wearing a face mask has been imposed in public places to keep the pandemic under control. However, face occlusion due to wearing a mask presents an emerging challenge for face recognition systems. In this paper, we present a solution to improve masked face recognition performance. Specifically, we propose the Embedding Unmasking Model (EUM) operated on top of existing face recognition models. We also propose a novel loss function, the Self-restrained Triplet (SRT), which enabled the EUM to produce embeddings similar to these of unmasked faces of the same identities. The achieved evaluation results on three face recognition models, two real masked datasets, and two synthetically generated masked face datasets proved that our proposed approach significantly improves the performance in most experimental settings.

Freie Schlagworte: Biometrics, Face recognition, Deep learning, Machine learning
Zusätzliche Informationen:

Art.No.: 108473

Fachbereich(e)/-gebiet(e): 20 Fachbereich Informatik
20 Fachbereich Informatik > Graphisch-Interaktive Systeme
20 Fachbereich Informatik > Mathematisches und angewandtes Visual Computing
Hinterlegungsdatum: 16 Feb 2022 08:21
Letzte Änderung: 16 Feb 2022 08:21
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