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

• Tipo: Artigo em Livro de Atas de Conferência Internacional
• Data: 2021

Autores

Neto, PC (Autor) Outra; Boutros, F (Autor) Outra; Pinto, JR (Autor) Outra; Saffari, M (Autor) Outra; Damer, N (Autor) Outra; Sequeira, AF (Autor) Outra; Jaime S Cardoso (Autor) FEUP

Ata de Conferência Internacional

Título: PROCEEDINGS OF THE 20TH INTERNATIONAL CONFERENCE OF THE BIOMETRICS SPECIAL INTEREST GROUP (BIOSIG 2021)

Páginas: 21-30

20th Annual International Conference of the Biometrics-Special-Interest-Group (BIOSIG )

ELECTR NETWORK, SEP 15-17, 2021

Indexação

ISI Web of Knowledge - 7 Citações

Scopus - 13 Citações

Outras Informações

ID Authenticus: P-00V-7VN

DOI: 10.1109/biosig52210.2021.9548320

Abstract (EN): 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.

Idioma: Inglês

Tipo (Avaliação Docente): Científica

Nº de páginas: 5