Mask Detection Analysis Using Haar Cascade and Naïve Bayes

Abstract

Coronavirus Disease (COVID-19) is a new virus variant that emerged in 2019. The World Health Organization (WHO) states that 394,381,395 people have been infected with COVID-19, and 5,735,178 have died. This epidemic has been found in Indonesia since March 2020. New cases in Indonesia are still increasing every day as a whole. The Government as a policy has imposed a policy on anyone who will be required to wear a mask and also carry out physical distancing so that they can work without the maker being exposed to the virus. In the midst of a pandemic, the use of masks has increased to prevent transmission. Various types of masks are easy to find, but not all masks are recommended to avoid transmission. Among them are the N-95 masks, which are recommended to prevent transmission. This application uses the haar cascade and naive bayes methods. The pycharm edition 2021.2 tools and python 3.8 are the detection systems used in this mask. The haar cascade method is also used in detecting objects with masks or not and naive Bayes, which is used as an accuracy calculation. This study uses a dataset of 1092, which is divided into 192 positive images and 900 negative images. Accuracy results using the haar cascade method are 100% more accurate, while the nave Bayes method is 76.6% less accurate.