ABSTRACT
The COVID-19 pandemic has infected tens of millions of individuals around the world, and it is currently posing a worldwide health calamity. Wearing a face mask in public places is one of the most effective protection strategies, according to the World Health Organization (WHO). Moreover, their effectiveness has declined due to incorrect use of the face mask. In this scenario, effective recognition systems are anticipated to ensure that people's faces are covered with masks in public locations. Many people do not correctly wear the masks due to inadequate practices, undesirable behaviour, or individual vulnerabilities. As a result, there has been an increase in demand for automatic real-time face mask detection and mask position detection to substitute manual reminders. This proposed work classifies people into three categories such as with mask, without mask and mask with incorrect position. The dataset is tested using three different variants of object detection models, namely YOLOv4, Tiny YOLOv4, and YOLOv5. The experimental result shows that YOLOv5 model outperforms with the highest mAP value of 99.40% compared to the other two models. Copyright © 2023 Inderscience Enterprises Ltd.
ABSTRACT
The COVID-19 pandemic has infected tens of millions of individuals around the world, and it is currently posing a worldwide health calamity. Wearing a face mask in public places is one of the most effective protection strategies, according to the World Health Organization (WHO). Moreover, their effectiveness has declined due to incorrect use of the face mask. In this scenario, effective recognition systems are anticipated to ensure that people's faces are covered with masks in public locations. Many people do not correctly wear the masks due to inadequate practices, undesirable behaviour, or individual vulnerabilities. As a result, there has been an increase in demand for automatic real-time face mask detection and mask position detection to substitute manual reminders. This proposed work classifies people into three categories such as with mask, without mask and mask with incorrect position. The dataset is tested using three different variants of object detection models, namely YOLOv4, Tiny YOLOv4, and YOLOv5. The experimental result shows that YOLOv5 model outperforms with the highest mAP value of 99.40% compared to the other two models.
ABSTRACT
COVID-19’s is a novel corona virus, fast spread has caused substantial damage and affected more than tens of millions of individuals around the world. People frequently wear masks to safeguard themselves and others against the transmission of coronavirus. The world health organization conveys the people to follow the social distancing to prevent the spread of Covid. Researchers have proposed several machine learning models to classify the disease, but none have identified the algorithm which gives more accuracy. Also, similar studies that have proposed various other techniques for prediction. In addition to that maintaining social distancing is also a major factor. In these regions, personally monitoring whether individuals are maintaining social distancing or not is quite impossible. This study aims to develop a highly accurate and real-time technique for the automatic detection of individuals who are not maintaining social distancing. Three state-of-the-art object identification models, namely YOLOv4, Tiny-YOLOv4 are used to detect the objects. Many results suggest that YOLO v4 has the greatest mAP value of 88.90%, followed by YOLO v4 and Tiny-YOLO v4 with mAP values of 82.24% and 74.80%, respectively. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.