A Siamese Neural Network-Based Face Recognition from Masked Faces

ABSTRACT

In modern days, face recognition is a critical aspect of security and surveillance. Face recognition techniques are widely used for mobile devices and public surveillance. Occlusion is a challenge while designing face recognition applications. In the COVID19 pandemic, we are advised to wear a face mask in public places. It helps us prevent the droplets from entering our body from a potential COVID19 positive person’s nose or mouth. However, it brings difficulty for the security personnel to identify the human face by seeing the partially exposed face. Most of the existing models are built based on the entire human face. It could either fail or perform poorly in the scenario as mentioned above. In this paper, a solution has been proposed by leveraging Siamese neural network for human face recognition from the partial human face. The prototype has been developed on the celebrity faces and validated with the state-of-the-art VGGFace2 (Resnet50) model. Our proposed model has performed well and provides very competitive results of 93% and 84.80 ± 4.71 % best-of-five and mean accuracy for partial face-images, respectively. © 2022, Springer Nature Switzerland AG.