Using COVID-19 Masks Dataset to Implement Deep Convolutional Neural Networks For Facial Emotion Recognition

Abstract

In light of the novel pandemic called COVID-19, the world has been instructed to wear protective facial masks to limit its spread. Doing so has reduced the effectiveness of traditional facial recognition technologies, especially in processing human facial emotions. This has rendered the usage of such technology obsolete in managing facial databases, relying on it for security purposes, and so on. It is then necessary to enhance the current generation of facial recognition to adapt to the protective masks. Speaking of the current facial recognition generation, most of its complex iterations heavily rely on deep learning, which is flawed since the existing facial databases are insufficient, making it even more inadequate to bypass facial masks. This is why the present research paper suggests implementing the Deep Convolutional Neural Networks (DCNN) algorithm using the Japanese Female Facial Expression (JAFFE) to simulate a masked face emotion recognition. This facial database is available free for academic research, was utilized to label the available images displaying various facial emotions under the umbrella of one of the seven basic human facial emotions, allowing for a more advanced facial technology. Consistent with the latest research findings, the proposed facial emotion recognition attains up to an accuracy of 71.35% due to its meticulous masked facial database.