ABSTRACT
The Coronavirus Disease (COVID-19) pandemic [1] is causing a public health crisis. One of the most helpful methods to treat the disease is to wear a face mask. This paper describes a facemask detection method that authorities may use to develop COVID-19 mitigation, evaluation, prevention, and response plans. FaMaDAS – Face Mask Detection and Alert System for COVID 19 is proposed in this work, which uses Machine Learning to identify fine-grained wearing state of a facemask, such as face without mask, face with suitable mask, and face with wrong mask. Face mask identification was achieved in this study using a binary classifier based on supervised learning algorithm. Collecting data, pre- processing, splitting data, testing model and implementing models are phases in developing model. The main aspect of the model is that anytime a CCTV camera detects a person without a face mask, an alarm message is sent to the individual as well as the necessary authorities, and a report is created. The built model can recognize whether or not someone is wearing a face mask with a 98 percent accuracy rate. On the basis of Training Accuracy and Loss, Validation Accuracy and lost the testing result reveals that FaMaDAS is adoptable and can be implement in today’s pandemic scenario. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.