(IJACSA) International Journal of Advanced Computer Science and Applications, Vol. 13, No. 11, 2022 Contactless Surveillance for Preventing Wind-Borne Disease using Deep Learning Approach Md Mania Ahmed Joy 1 Department of CSE East West University, Dhaka, Bangladesh Israt Jaben Bushra 2 Department of CSE East West University, Dhaka, Bangladesh Razoana Ayshee 3 Department of CSE East West University, Dhaka, Bangladesh Samira Hasan 4 Department of CSE East West University, Dhaka, Bangladesh Samia Binta Hassan 5 Department of CSE East West University, Dhaka, Bangladesh Md. Sawkat Ali 6 Department of CSE East West University, Dhaka, Bangladesh Prof.Dr. Omar Farrok 7 Department of EEE Ahsanullah University of Science and Technology, Dhaka,Bangladesh Mohammad Rifat Ahmmad Rashid 8 Department of CSE East West University, Dhaka, Bangladesh Maheen Islam 9 Department of CSE East West University, Dhaka, Bangladesh Abstract—Covid-19 has been marked as a pandemic world- wide caused by the SARS-CoV-2 virus. Different studies are being conducted with a view to preventing and lessening the infections caused by covid-19. In future, many other wind-borne diseases may also appear and even emerge as “pandemic”. To prevent this, various measures should be an integral part of our daily life such as wearing face masks. It is tough to manually ensure individuals safety. The goal of this paper is to automate the process of contactless surveillance so that substantial prevention can be ensured against all kinds of wind-borne diseases. For automating the process, real time analysis and object detection is a must for which deep learning is the most efficient approach. In this paper, a deep learning model is used to check if a person takes any preventive measures. In our experimental analysis, we considered real time face mask detection as a preventive measure. We proposed a new face mask detection dataset. The accuracy of detecting a face mask along with the identity of a person achieved accuracy of 99.5%. The proposed model decreases time consumption as no human intervention is needed to check an individual person. This model helps to decrease infection risk by using a contactless automation system. Keywords—Computer vision; convolution neural network; COVID-19; deep learning; face mask detection; identity detection; object detection I. I NTRODUCTION Whenever the world faced any pandemic, history witnessed a pessimistic effect on economics, health, and national security both socially and globally [1]. Before the COVID-19, H1N1 or influenza was marked as a pandemic in the year 2009 [2] [3]. The COVID stands for “CoronaVirus Disease”, it is referred to as “2019 novel coronavirus” or “2019-nCoV” as it was started in 2019 [4]. Form the beginning of this pandemic, around 228 countries have been affected by the COVID-19 to date [4]. The rapid growth of the COVID-19 infected cases has put the national healthcare capacity, modern ICU diagnostic methods, and public healthcare infrastructure to a test. For instance, Bangladesh has less than 7,000 spaces in iso- lation units and therefore only 1622 health workers, including only 595 physicians to treat COVID-19 patients, whereas it has a population of about 165 million people [5]. On the other hand, the United States (US), which like Europe, spends about double as much per person on healthcare insurance as those other high-income counties, has drawn special criticism for its “maximum-possible-test-per-day” policy and use of its 96,596 ICU beds [5]. Overall, it became a chaotic situation which completely caught the whole world off guard. To prevent this disease, many effective vaccines have been invented [6] but these vaccines are not sufficient to give full protection to the people to prevent the COVID-19. So, people had to follow some non-therapeutic prohibitive measures like maintaining social distance, travel bans, remote office activities, country lockdown, wearing masks, etc. despite being vaccinated Since 2019 almost all the nations of the world are strug- gling to get out of this misery. This kind of prohibition rules put a financial crisis as lockdown remains on all kinds of institutions [7]. In [8], according to the “Socio-Economic Aspects” about 60.5% of the respondents agreed that most of the low incoming people lost their jobs and around 54.8% of people also shifted to different places by leaving the city for livelihood. To ease the survival challenge of the people who lived from hand to mouth, the lockdown had to be lifted. Then there comes another challenge of ensuring that every individual wear masks in their working places. To ensure security in institutions or industries, many automation systems exist that can identify the registered person One of them is a biometric system that works with measurements and by analyzing someone’s unique features. Physical unique features like face, irises, veins, fingerprints, and behavioral characteristics such as voice, typing rhythm, or handwriting, is used for identification and authentication [9]. These systems are not contactless, and these require removing www.ijacsa.thesai.org 775 | Page