JMIR Publications

ABSTRACT

Background:

COVID-19 has affected the entire world. One useful protection method for people against COVID-19 is to wear masks in public areas.

Objective:

In this study we quantify the mask usage by analysing 2.04 social media images and find correlate it with the COVID-19 cases in those states and the movement restrictions imposed by their respective governments

Methods:

We propose a framework for classifying masked and unmasked faces and a segmentation based model to calculate the mask-fit score. Both the models trained in this study achieved an accuracy of 98%. Using the two trained deep learning models, 2.04 million social media images for six major US cities were analyzed.

Results:

Along with building a deep-learning mask classifier and mask-fit analyser, we open-source one of the largest dataset for face-mask classification tasks: VAriety MAsks - Classification (VAMA-C) and the world’s only dataset for mask-fit analysis tasks: VAriety MAsks - Segmentation (VAMA-S).

Conclusions:

By comparing the regulations, an increase in masks worn in images as the COVID-19 cases rose in these cities was observed, particularly when their respective states imposed strict regulations. Furthermore, mask compliance in the Black Lives Matter protest was analyzed, eliciting that 40% of the people in group photos wore masks, and 45% of them wore the masks with a fit score of greater than 80%.