Social distance and face mask detector system exploiting transfer learning

As time advances, the use of deep learning-based object detection algorithms has also evolved leading to developments of new human-computer interactions, facilitating an exploration of various domains. Considering the automated process of detection, systems suitable for detecting violations are developed. One such applications is the social distancing and face mask detectors to control air-borne diseases. The objective of this research is to deploy transfer learning on object detection models for spotting violations in face masks and physical distance rules in real-time. The common drawbacks of existing models are low accuracy and inability to detect in real-time. The MobileNetV2 object detection model and YOLOv3 model with Euclidean distance measure have been used for detection of face mask and physical distancing. A proactive transfer learning approach is used to perform the functionality of face mask classification on the patterns obtained from the social distance detector model. On implementing the application on various surveillance footage, it was observed that the system could classify masked and unmasked faces and if social distancing was maintained or not with accuracies 99% and 94% respectively. The models exhibited high accuracy on testing and the system can be infused with the existing internet protocol (IP) cameras or surveillance systems for real-time surveillance of face masks and physical distancing rules effectively. © 2022 Institute of Advanced Engineering and Science. All rights reserved.

Machine Learning based Face Mask Classifier

The COVID19 pandemic has affected almost entire world. The virus is spreading at a rapid rate through droplets generated while sneezing or coughing. All the governments in the world have made it mandatory to wear face masks. But almost 30 to 40% of public is not following the rules. Some people wear masks but they do not wear them in a proper way i.e., they wear masks below their nose. This paper proposes a model based on InceptionV3 algorithm which classifies people into 3 categories namely: face fully covered, face not covered and face partially covered with mask. This paper will help the police to detect people without masks or people not wearing masks properly at a crowded place. The police can then keep record of such people and fine them. © 2022 IEEE.

Detection of Face Mask Using Convolutional Neural Network

According to data acquired by the World Health Organization, the worldwide universal of COVID-19 bears harshly hit the realm and bears immediately contaminate eight heaps of human beings in general. Wearing face masks and following cautious public leave behind are two of the embellished protection from harm rules of conduct that need to take the place of honestly held places in consideration of keeping from happening or continuing the spread of the virus. To develop in mind or physically conservative surroundings that contribute to public protection from harm, we suggest an adept data processing machine located in close contact with the genuine in existence-period made or done by a human being to discover two reliable public dissociate themselves and face masks honestly placed by the model ahead of the start of the model to monitor special interests or pursuits and discover rape through photographic equipment. In addition to presenting an alarm to the public, in this proposed structure, we have designed mask detection along which indicates people to wear their mask properly before permitting in to the area which they prefer. We have used machine learning with supports the accuracy for the prediction. © 2022 IEEE.