Masked Face Recognition Dataset and Application

During COVID-19 coronavirus epidemic, almost everyone wears a mask to prevent the spread of virus. It raises a problem that the traditional face recognition model basically fails in the scene of face-based identity verification, such as security check, community visit check-in, etc. Therefore, it is imminent to boost the performance of masked face recognition. Most recent advanced face recognition methods are based on deep learning, which heavily depends on a large number of training samples. However, there are presently no publicly available masked face recognition datasets, especially real ones. To this end, this work proposes three types of masked face datasets, including Masked Face Detection Dataset (MFDD), Real-world Masked Face Recognition Dataset (RMFRD) and Synthetic Masked Face Recognition Dataset (SMFRD). Besides, we conduct benchmark experiments on these three datasets for reference. As far as we know, we are the first to publicly release large-scale masked face recognition datasets that can be downloaded for free at https://github.com/X-zhangyang/Real-World-Masked-Face-Dataset.

I. Introduction

During the COVID-19 coronavirus epidemic, wearing a mask has become an effective means for people to prevent the spread of the virus. In this case, the traditional face recognition technology based on full facial features information is almost ineffective, which has brought huge dilemmas to face-based authentication applications, such as face access control, face gates, face authentication, etc. Especially in the security check at the railway station, the face recognition system usually rejects the masked faces, but taking off the mask to pass the authorization will increase the risk of virus transmission. In view of the characteristics of virus contact infection, the authorization method based on password and fingerprint is not safe. Face recognition, a convenient contactless verification method, is even more secure. However, the existing face recognition is no longer reliable when encountering masked faces. Therefore, it is meaningful and imminent to develop a mask-robust face recognition model.