Deep Neural Architecture for Face mask Detection on Simulated Masked Face Dataset against Covid-19 Pandemic

Aim:

To apply the Deep Learning techniques based on convolution neural network improving the face mask detector accuracy.

Synopsis:

             The corona virus disease 2019 (COVID-19) has globally infected over 2.7million people and caused over 180,000 deaths. There are several similar large scale serious respiratory diseases, such as severe acute respiratory syndrome (SARS) and the Middle East respiratory syndrome (MERS), which occurred in the past few years. Therefore, more and more people are concerned about their health, and public health is considered as the top priority for governments. Furthermore, many public service providers require customers to use the service only if they wear masks. Face mask detection has become a crucial computer vision task to help the global society, but research related to face mask detection is limited.

Proposed System:

          We propose Retina Face Mask, which is a high-accuracy and efficient face mask detector. The proposed Retina Face Mask is a one-stage detector, which consists of a feature pyramid network to fuse high-level semantic information with multiple feature maps, and a novel context attention module to focus on detecting face masks. Face mask detection refers to detect whether a person wearing a mask or not.