Efficiency for Face Mask Detection in Neural Network

Abstract

Because of COVID-19, wearing a face mask has become the most efficient and convenient way to spread this virus. Face mask detection can fulfill the function of warning those people who do not wear a face mask. Using the Convolutional neural network, the Feedforward Neural Network and the MobileNet V2, a high recognition rate for the face mask detecting system can be achieved. This study compares the accuracy, the loss and the training time for these models and concludes that CNN is the best model based on its high accuracy of 100%. The result that comes out from our study can improve the efficiency of the face mask detecting system. In general, the identification model in our study can be changed easily to apply in other areas, such as medical image classification and geographic image classification.