A practical implementation of mask detection for COVID-19 using face detection and histogram of oriented gradients

ABSTRACT Wearing a face mask is one of the effective barriers against the coronavirus COVID-19 pandemic. It offers protection according to the World Health Organization and many medical papers. This paper proposes a method for masked face recognition in order to force the population to put on masks and reduce the COVID-19 pandemic in the world. The Viola-Jones algorithm is used to detect the face, and the Histogram of Oriented Gradients (HOG) technique was used to extract the relevant features from face images. The performance of the proposed algorithm is analysed for different data using two common image classification methods, including support vector machines and K Nearest Neighbor (KNN) algorithm for machine learning, which are used to classify the feature vectors. Their performance was compared and evaluated using accuracy. In this case, the experimental result shows that the support vector machine classifier achieved the highest accuracy and surpasses the KNN method in mask detection with an accuracy of 99.43%.