Deep Learning Based Face Mask Detection System for COVID-19 Control

COVID-19 pandemic is spreading continuously causing serious health problems. Wearing face mask is one of the prominent precautions people can easily follow. In this paper, we have built a model for face-mask detection system using deep learning technique that uses Histogram of Oriented Gradients (HOG) based features for face detection and Convolutional Neural Network (CNN) for detecting whether the person is wearing face mask or not. The model has also the capability of detecting whether the wearer is wearing the face mask properly or not. This model has been trained with 3650 images using python script in Google Colab environment applying Keras and TensorFlow. After a number of trials we have found that our model gives best result with 50 epochs. We have found training and validation accuracy 94.59% and 98.51% respectively. The model has been tested with real time inputs. From the experimental results it has been found that the proposed model is capable of detection faces with-mask and without-mask with 97% accuracy.