Face Mask Detection on LabVIEW

Abstract

The world is facing a huge health crisis due to the coronavirus pandemic (COVID-19). The World Health Organization (WHO) has issued that the most effective preventive measure against the rapid spread of coronavirus is wearing a mask and keeping social distance in public places and crowded areas. Various studies have proven that wearing a face mask significantly reduces the risk of viral transmission, and also provides a sense of protection for people. But it is difficult to monitor and control people manually, especially in crowded areas. In this study, a deep learning model is proposed to automatically detect people wearing face masks or not. The pre-trained Faster R-CNN Inception V2 deep learning model is fine-tuned with the transfer learning method and trained and tested on the Simulated Masked Face Dataset (SMFD). The model trained in the TensorFlow environment is accurate enough to detect the face mask. Thus, face mask detection is performed with the interface created on LabVIEW and a safe working environment can be maintained by controlling security violations in public living areas under control.