Facemask and social distancing detection system using image processing /
Gerald L. Lipata, Shainah L. Perez, Pamela B. Piliotas, Aaron E. Viray .--
- Manila: Technological University of the Philippines, 2023.
- 90pages: 29cm.
Bachelor's thesis
College of Industrial Technology .--
Includes bibliographic references and index.
The COVID-19 pandemic has raised significant concerns globally, particularly the rapid spread of the virus and the importance of wearing masks and practicing social distancing. There are various methods used to overcome rapid spread of COVID-19 in schools which are found to be reliable in detecting safe distance between individuals in public places. However, they are found out to be inaccurate in measuring the distance and face detection between people due to distortion caused by perspective in images. Hence, the researchers designed, developed, tested and evaluated the system "Facemask and Social Distancing Detection System using Image Processing" using convolutional neural network. The hypothesis testing results prove that there is no significant difference on the accuracy of detecting facemask : (M= 0.2521, SD = 0.0118) while the detected person not wearing mask (M= 0.2459, SD = 0.0139); t (15.180) = 0.846; p = 0.411; a = 0.025 using the Independent T-test and there is no significant difference on the timeliness of social distancing: (M = 0.2512, SD = 0.0107); F (2, 27) = 0.748; p = 0.483 and a sample size of n=10 using the Analysis of Variance (ANOVA). This means that the system is significantly accurate and consistently timely in detecting facemask and social distancing. Moreover, participants rated the system a numerical rating of 4.78 for its performance, usability, functionality, and satisfaction making it "excellent". Overall, the study aligns with the United Nations Sustainable Development Goals (UN-SDGs) 3 and 6, which focuses on ensuring healthy lives and promote well-being for all ages and ensuring the availability and sustainability management of water and sanitation for all.