My Eyes Are Up Here: Promoting Focus on Uncovered Regions in Masked Face Recognition
This addresses the problem of degraded face recognition accuracy due to mask-wearing during the Covid-19 pandemic, but it is incremental as it builds on existing loss functions.
The paper tackled the challenge of masked face recognition by proposing a method combining triplet loss and mean squared error to improve verification performance when comparing masked to unmasked faces, showing significant performance gains in ablation studies on two databases.
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.