Hybrid CNN-SVM Model for Face Mask Detector to Protect from COVID-19

Abstract

The 2019 coronavirus outbreak (COVID-19) has had a huge impact on humanity. By May 2021, nearly, 172 million people worldwide were affected by the infectious spread of COVID-19. While the distribution of vaccines has already begun, mass distribution around the world has yet to take place. According to the World Health Organization (WHO), wearing a face mask can significantly reduce the spread of the COVID-19 virus. However, even improper wearing of face mask can prevent the purposes and lead to the spread of the virus. Under the influence of public health and the global economy, an effective Covid-19 pandemic strategy requires a lot of attention of humanity. To prevent the spread of such deadly virus, intelligent techniques are required. In the proposed work, an intelligent face mask detector framework is proposed based on deep learning concept which can classify the person who wear mask from those who are not wearing mask. In the proposed work, a hybrid model of convolution neural network with support vector machine is used for designing the mask detector. The performance of the proposed method is evaluated on real-world masked face recognition dataset (RMFD) and medical mask dataset (MDD). When implemented, it has been found that the proposed method can achieve high accuracy (99.11%). The excellent performance of the proposed model is very suitable for video surveillance equipment also.