HybridFaceMaskNet: A Novel Face-Mask Detection Framework Using Hybrid Approach

Abstract Coronavirus disease 2019 (covid-19 ) is a contiguous disease which is caused by severe acute respiratory syndrome coronavirus2(SARAS-2) started from Wuhan, china, and spread all over the world within a few months in 2019. Government of all countries had to apply lockdown to decrease the number of affected patient as mortality rate of many countries became very high at that time. In the awake of 2nd wave of COVID 19 WHO has made mandatory to use mask in largely crowded areas, health centers, communities and in different places to prevent spread of virus. Many countries have invented the vacancies but it will firstly available for corona front line warriors only, not for general people, So, people have to wear mask when they are going out from home. But In recent days it can be followed that people are reluctant to wear mask when they are entering in offices, departmental stores or local shops where, gathering might happen anytime. This could lead to spread of COVID-19 among the communities. With the help of computer-vision, people who are not wearing mask can be detected by generating an alarm signal. To achieve this challenging task, a face mask detector ‘HybridFaceMaskNet’ is proposed, which is a combination of classical Machine Learning and deep learning algorithm. ‘HybridFaceMaskNet’ can achieve state-of-art accuracy on public faces. The real challenges are the low-quality images, different distances of people from camera and dynamic lighting on the faces at daylight or in artificial light.This problem can be overcome by using different noise removal techniques. HybridFaceMaskNet is trained with three different classification of images ‘proper-mask’, ‘incorrect-mask’ and ‘no-mask’ which are collected from real life images and some synthetic data , to generate alarm for different scenario .This HybridFaceMaskNet is trained on Google Colab and is compared with different existing face mask detector model. There is a possibility of deploy the model in IOT devices as it is light weight compare to other existing models.