Face Mask Detection Using Machine Learning Techniques

Abstract

The year 2020 will be remembered for a major pandemic caused by Covid-19. The studies have shown that the spread of corona virus can be slowed by using face mask and at crowded places where the transmission is high, the use of face mask is important. To determine whether the person is wearing the face mask or not plays a major role which is done using face mask detection. The main objective is to develop a system to detect whether a person is wearing face mask or not wearing the face mask and to test the performance of different CNN models like Vgg16, MobileNetV2 and Densenet121 which can be used for classification. The models were compared with respect to accuracy, AUC curve, confusion matrix and its accuracy of predicting the image if it is with face mask or without face mask. The accuracy of Vgg16, MobileNetV2 and Densenet121 was found to be 93.1%, 99.88% and 99.37% respectively. The area under the ROC curve for the densenet121 was found to be greater as compared to other models. The models were also tested with respect to the confusion matrix and predicting if a person is wearing the face mask or not wearing the face mask.