Abstract

Recently, the coronavirus pandemic has made the use of facial masks and respirators common, the former to reduce the likelihood of spreading saliva droplets and the latter as Personal Protective Equipment (PPE). As a result, this caused problems for the existing face detection algorithms. For this reason, and for the implementation of other more sophisticated systems, able to recognize the type of facial mask or respirator and to react given this information, we created the Facial Masks and Respirators Database (FMR-DB).

The database consists of 2565 images taken from the Internet, divided into the following main classes:

With Facial Mask or Respirator

Disposable Respirators With Valve
Disposable Respirators Without Valve
Full-Face Respirators
Half-Face Respirators
Non-Medical Masks
Surgical Masks

Without Facial Mask or Respirator

With Occlusions

Hands On Mouth
Hats
Neck Warmers And Bandanas
Sunglasses

Without Occlusions

Images depicting people wearing a mask or a respirator also have a classification on the additional protective clothing worn: eye protection, head protection or both. The images depicting people wearing disposable respirators are also classified according to the respirator protection class.

This dataset was recently presented and tested in the "Recognizing the Type of Mask or Respirator Worn Through a CNN Trained with a Novel Database" paper at the 2021 IEEE 45th Annual Computers, Software, and Applications Conference (COMPSAC). You can find it at this link: https://dx.doi.org/10.1109/COMPSAC51774.2021.00221

Instructions:

For reasons related to the copyright of the images, we cannot publish the entire database here. If you are a student, a professor, or a researcher and you want to use it for research purposes, send an email to antonio.marceddu@polito.it attaching the license, duly completed, which you can find here on IEEE DataPort.