Self-restrained Triplet Loss for Accurate Masked Face Recognition
This addresses a practical challenge for biometric security systems in public health contexts, though it appears incremental as it builds on existing face recognition models.
The paper tackles the problem of face recognition accuracy degradation when subjects wear masks by proposing an Embedding Unmasking Model (EUM) with a Self-restrained Triplet (SRT) loss function, which significantly improved performance across multiple models and datasets.
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.