Implementation of Deep Learning in Order to Detect Inapposite Mask User

Abstract

The number of COVID-19 patients that continues to increase, has made several countries continue to seek treatment so that they can help COVID-19 patients recover. The increasing number of patients is indicated, because many residents still do not comply with health protocols. WHO explains that one of the important protocols is to use masks correctly. Some residents are reluctant to use masks because it makes communication less clear and breathless. Due to these omissions, this study aims to identify the use of masks. This study is able to identify the proper use of masks, the use of inappropriate masks and the face without a mask. The process of this research begins with creating a training model from several images. The model that has been made is used as a reference for identification using CNN. The results of the accuracy of this study reached "99.35%".