Masked face with facial expression recognition based on deep learning

Abstract

Wearing masks contributed to slowing the spread of the coronavirus disease (COVID-19) as the World Health Organization (WHO) recommended wearing face masks especially with the spreading of virus variants like omicron. Although people accept the idea of wearing these masks, it is still unknown the effect of covering parts of the face on social interaction among people in general and children in particular. Moreover, Social isolation affects emotional moods, which causes stress, sadness, and depression. In the current study, we have been exploring the emotional inferences on faces with and without a mask. The system can pick up the universal emotions: fear, disgust, anger, surprise, contempt, sadness, and happiness. The researchers in deep learning are concerned with global pandemic COVID-19 to enhance public health service. The proposed model is developed with a machine learning algorithm through the Haar feature-based cascade classifiers. The built model can detect people's emotions with mask and without a mask with high accuracy.