Face recognition has become relevant in the search for non-physical contact solutions in enclosed spaces for identity verification in the context of the SARS-CoV-2 pandemic. One of the challenges of face recognition is mask occlusion which hides more than 50 % of the face. This research evaluated four models pre-trained by transfer learning: VGG-16, RESNET-50, Vision Transformer (ViT), and Swin Transformer, trained on their upper layers with a proprietary dataset. The analysis obtained an accuracy of 24 % (RESNET-50), 25 % (VGG-16), 96 % (ViT), and 91 % (Swin) with unmasked subjects. While with a mask, accuracy was 32 % (RESNET-50), 53 % (VGG-16), 87 % (ViT), and 61 % (Swin). These percentages indicate that modern architectures such as the Transformers perform better in mask recognition than the CNNs (VGG-16 and RESNET-50). The contribution of the research lies in the experimentation wit...

In the context of the pandemic, face recognition became important as a non-physical contact verification method. Thus, this research evaluated the accuracy of pre-trained models (VGG-16, RESNET-50, Vision Transformer, Swin Transformer) for identity verification, facing the challenge of mask occlusion. The results revealed that the transformer models outperformed the CNNs in accuracy. This work contributes significantly by exploring two types of architectures and creating a public dataset, enriching computer vision research for face recognition with mask occlusion.

Face recognition has become relevant in the search for non-physical contact solutions in enclosed spaces for identity verification in the context of the SARS-CoV-2 pandemic. One of the challenges of face recognition is mask occlusion which hides more than 50 % of the face. This research evaluated four models pre-trained by transfer learning: VGG-16, RESNET-50, Vision Transformer (ViT), and Swin Transformer, trained on their upper layers with a proprietary dataset. The analysis obtained an accuracy of 24 % (RESNET-50), 25 % (VGG-16), 96 % (ViT), and 91 % (Swin) with unmasked subjects. While with a mask, accuracy was 32 % (RESNET-50), 53 % (VGG-16), 87 % (ViT), and 61 % (Swin). These percentages indicate that modern architectures such as the Transformers perform better in mask recognition than the CNNs (VGG-16 and RESNET-50). The contribution of the research lies in the experimentation wit...