ABSTRACT
Due to the global spread of the Covid-19 virus and its variants, new needs and problems have emerged during the pandemic that deeply affects our lives. Wearing masks as the most effective measure to prevent the spread and transmission of the virus has brought various security vulnerabilities. Today we are going through times when wearing a mask is part of our lives, thus, it is very important to identify individuals who violate this rule. Besides, this pandemic makes the traditional biometric authentication systems less effective in many cases such as facial security checks, gated community access control, and facial attendance. So far, in the area of masked face recognition, a small number of contributions have been accomplished. It is definitely imperative to enhance the recognition performance of the traditional face recognition methods on masked faces. Existing masked face recognition approaches are mostly performed based on deep learning models that require plenty of samples. Nevertheless, there are not enough image datasets containing a masked face. As such, the main objective of this study is to identify individuals who do not use masks or use them incorrectly and to verify their identity by building a masked face dataset. On this basis, a novel real-time masked detection service and face recognition mobile application was developed based on an ensemble of fine-tuned lightweight deep Convolutional Neural Networks (CNN). The proposed model achieves 90.40% validation accuracy using 12 individuals' 1849 face samples. Experiments on the five datasets built in this research demonstrate that the proposed system notably enhances the performance of masked face recognition compared to the other state-of-the-art approaches.
ABSTRACT
BACKGROUND: Corona virus disease 2019 (COVID-19) has been announced as a new coronavirus disease by the World Health Organization. At the time of writing this article (April 2020), the world is drastically influenced by the COVID-19. Recently, the COVID-19 Open Research Dataset (CORD-19) was published. For researchers on ID such as ourselves, it is of key interest to learn whether this open research dataset may be used to investigate the virus and its consequences for people with an ID. METHODS: From CORD-19, we identified full-text articles containing terms related to the ID care and applied a text mining technique, specifically the term frequency-inverse document frequency analysis in combination with K-means clustering. RESULTS: Two hundred fifty-nine articles contained one or more of our specified terms related to ID. We were able to cluster these articles related to ID into five clusters on different topics, namely: mental health, viral diseases, diagnoses and treatments, maternal care and paediatrics, and genetics. CONCLUSION: The CORD-19 open research dataset consists of valuable information about not only COVID-19 disease but also ID and the relationship between them. We suggest researchers investigate literature-based discovery approaches on the CORD-19 and develop a new dataset that addresses the intersection of these two fields for further research.