Abstract
As the world is engulfed with COVID-19 pandemic and the glimpse of vaccine is still a distant dream, taking precautions and maintaining the norms suggested by WHO will keep us safe. With this, we present in this paper a solution that would help travelers induce confidence in traveling while keeping in mind the guidelines that must be followed. The solution focuses on an end to end service that will not only help the travelers to make informed and safe decisions but also allow the hospitality industry to monetize from this application. This paper is focused on a detailed analysis of the solution that is being presented to tackle the problems faced by various industries and their fear of resuming the work. A software-based approach is taken for providing a simple and engaging user experience to the user along with an AI approach to detect and predict the COVID trend in various cities. Along with this, a system that detects if people are wearing a mask or not will also be verified by thealgorithm.
Highlights
It’s been nearly a century since pandemics have globally affected the lives of the people and the economy of many countries
From previous pandemics like the plague of Justinian, Smallpox which wiped out a large number of populations, COVID too can have a disastrous effect on mankind if proper precautions are not taken into account
An easy to use the website is made for all the travelers so that they can be sure about the COVID trend and the news of COVID and other important updates of the place of travel
Summary
It’s been nearly a century since pandemics have globally affected the lives of the people and the economy of many countries. By using Convolutional Neural Networks we achieved the task of detecting if people are wearing masks or not. This service can be used up by the hospitality industry like hotels and museums so that people visiting such places have an idea about the extent to which the WHO guidelines are being followed. Many implementations for detecting faces are based on using on the histogram of oriented gradients (HOG) followed by a linear SVM or pretrained networks such as YOLO or suing Single Shot Detection (SSD) For this implementation, a face detector based on CNN (Convolutional Neural Network) available in dlib was used.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
