WITHDRAWN: Masked face recognition with BF-FaceNet and multi-view features

Abstract

Wearing masks in accordance with scientific guidelines is the most economically-effective protective measure for preventing respiratory diseases, such as COVID-19 and influenza, by interrupting viral transmission and safeguarding one's own health. In fact, researchers found that wearing masks can effectively reduce the infection rate of COVID-19 by 65%. However, this brings great inconvenience to face recognition, and human face recognition accuracy under occlusion conditions is low. Therefore, this paper proposes masked face recognition with BF-FaceNet and multi-view features. Firstly, in order to extract fine-grained features of the face region, ResNet50 is replaced by BoTNet as the backbone network of FaceNet. Secondly, a non-masked map is generated to accurately locate the non-masked area. Meanwhile, the face attention augmentation model (FAAM) is designed to extract local face features of the non-masked map. Thirdly, by combining loss function Ltriplet with Lattention, joint loss function Lface is proposed to improve the accuracy of masked recognition. Finally, experimental results on the publicly-available masked face dataset, SMFRD, demonstrate a significant improvement in recognition accuracy using our proposed algorithm compared to other methods.