Face Mask Detection Using Deep Learning

ABSTRACT

COVID-19 pandemic is proving to be one of the biggest challenges faced by the world. Different safety measures are being taken by the governments such as lockdowns and mandatory application of face mask. Wearing a face mask is one of most efficacious methods of prevention according to the World Health Organisation (WHO). In this paper, a convolutional neural network model has been proposed which identifies whether a person is wearing a face mask or not. The model uses the robust TensorFlow library to work constructively. The model has been trained on an image dataset consisting of 3835 images where 1916 images are with face masks and 1919 images are of people without face mask. The images in the dataset has been collected from Bing Search API, Kaggle Datasets and RMFD Datasets. The proposed Deep Learning model gave an accuracy of 97.98% when trained on TensorFlow cpu 2.3.0 © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.