Face Mask Detection Using ResNet50 Model and fine tuning it on various hyperactive parameters

Abstract

The COVID-19 that took all the nations for a toll has increased interest in the logical field of facemask placement. This research determines if a person is appropriately wearing a face mask or is at danger of illness using computer vision and machine learning algorithms. The study uses multiple social datasets that show people wearing face coverings or not in photographs or videos. These datasets are used to create and implement machine learning models that can determine whether or not a person is wearing a face covering. In this work, faces covered under coverings are recognised using a ResNet50 Model. Next, it is improved for a number of hyper characteristics to forecast face photographs with an accuracy of 99 percent, aiding in the advancement of the investigation and the development of humanistic technology that will enhance sustainable development.