Automated Face Mask Detector Using Machine Learning: An Approach to Reduce Burden on Healthcare System

• Published in: 2023 4th International Conference on Smart Electronics and Communication (ICOSEC) pp. 1428 - 1433
• Main Authors: Singh, Retinderdeep, Prabha, Chander
• Format: Conference Proceeding
• Language: English
• Published: IEEE 20.09.2023
• Subjects: Convolutional Neural Network (CNN); COVID-19; Deep Learning; E-Commerce; Face Mask Detection; Machine Learning; Medical services; Next.js; Python; Real-time systems; Software; Streaming media; Surveillance; Training
• DOI: 10.1109/ICOSEC58147.2023.10276140

Taking the pandemic into consideration it is a prime step to work on the prevention aspect. Although the healthcare system is breaking down due to the increased spread of COVID-19 due to its transmission by airborne route through cough and sneezing, it urges the need to wear masks which includes personal protective equipment. Manual monitoring of individuals at public area entry is a challenging part for the administration so to ease out this problem automated surveillance system becomes the need of the hour. In this current study, a deep machine learning method is used to train the model by using an unstructured dataset through various resources with a sample size of 1000 masked and 1000 unmasked images of the individuals. The model has to undergo multiple layers of phases like the training phase, detection phase, and later providing an E-commerce platform for purchasing masks by linking it with a vending machine. The results were achieved with an accuracy of 99.8%, and a recall of 99%, indicating that the model is efficient in detecting face masks.