Open AccessFace Mask Recognition Using MobileNetV2
Author(s) -
Vivek Patel,
Dhruti Patel
Publication year - 2021
Publication title -
international journal of scientific research in computer science, engineering and information technology
Language(s) - English
Resource type - Journals
ISSN - 2456-3307
DOI - 10.32628/cseit1217519
Subject(s) - computer science , artificial intelligence , facial recognition system , face (sociological concept) , identification (biology) , computer vision , image (mathematics) , covid-19 , binary classification , pattern recognition (psychology) , machine learning , support vector machine , infectious disease (medical specialty) , medicine , social science , botany , disease , pathology , sociology , biology
The pandemic of Corona Virus Disease is generating a public health emergency. Wearing a mask is one of the most efficient ways to combat the infection. This paper presents the detection of face masks, through mitigating, evaluating, preventing, and preparing actions regarding COVID-19. In this work, face mask identification is achieved using Machine Learning technique and the Image Classification algorithms are MobileNetV2 with major changes which includes Label Binarizer, ImageNet, and Binary Cross-Entropy. The methods involved in building the model are collecting the data, pre-processing, image generation, model construction, compilation, and finally testing. The proposed method can recognize people with and without masks. The training accuracy of the proposed method is 98.5% and the testing accuracy is 99%. This model is implemented in an image or video stream to detect faces with mask.