Study on Face Mask Detector System in COVID-19 Era using Deep Learning
DOI:
https://doi.org/10.32628/CSEIT228326Keywords:
Deep Learning, Machine Learning, Artificial Neural Network, AI Models, Face-Mask Detection System, CNN, MobileNetV2Abstract
Due to worldwide pandemic COVID-19, there arises a severe need of protection mechanismsto prevent man-to-man infection and face mask is one of the most important protection mechanisms. The basic aim of this study is to detect the presence of a face mask on human faces on live streaming video as well as on static images. The concept of Face Mask Detection System using Convolutional Neural Networks is to provide thousands of images of masked and non-masked individuals to a computer program and then train the computer program to recognize and distinguish the individuals in those images as masked or unmasked. In the present study the authors will use deep learning to develop face detector model. The proposed technique takes place in 2 phases. The first phase includes fine tuning a pre-trained classifier with our data set. The second phase includes applying the highly trained classifier to detect faces with masks and no masks. Alongside this, we shall use basic concepts of transfer learning in neural networks to finally output presence or absence of a face mask in an image or a video stream.
References
- Shilpa Sethi, MamtaKathuria, Trilok Kaushik,2020, “Face mask detection using deep learning: An approach to reduce risk of Coronavirus spread”, “Journal of Biomedical Informatics”, Volume 120, ISSN 1532-0464.
- M. Inamdar, N. Mehendale, 2020, “Real-Time Face Mask Identification Using Facemasknet Deep Learning Network”, “SSRN Electronic Journal.”, Volume 221, ISSN 134-0156
- Artem Oppermann, 2017, “What is Deep Learning and How Does It Work?”, Available: https://towardsdatascience.com/what-is-deep-learning-and-how-does-it-work-2ce44bb692ac, Accessed: 12/10/2021
- SumitSaha, 2018, “A Comprehensive Guide to Convolutional Neural Networks”, Available: https://towardsdatascience.com/a-comprehensive-guide-to-convolutional-neural-networks-the-eli5-way-3bd2b1164a53, Accessed: 12/10/2021
- Mohit Varikkuti, 2021, “What is Tensorflow and how does it work?”, Available: https://towardsai.net/p/l/what-is-tensorflow-and-how-does-it-work, Accessed: 12/10/2021
- BalaVenkatest, 2020, “What is OPENCV and why do we need to know about it?”, Available: https://www.topcoder.com/thrive/articles/what-is-the-opencv-library-and-why-do-we-need-to-know-about-it, Accessed: 12/10/2021
- Martin Heller, 2019, “What is Keras? The deep neural network API explained”, Available: https://www.infoworld.com/article/3336192/what-is-keras-the-deep-neural-network-api-explained.html, Accessed: 12/10/2021
- Jason Brownlee, 2017 “A Gentle Introduction to Transfer Learning for Deep learning”, Available: https://machinelearningmastery.com/transfer-learning-for-deep-learning/, Accessed: 14/10/2021
- Sandler et al, 2018, “MobileNetV2: Inverted Residuals and Linear Bottlenecks”, Available: https://paperswithcode.com/paper/mobilenetv2-inverted-residuals-and-linear, Accessed 14/10/2021
- Francois Chollet, 2020, “Transfer Learning and Fine Tuning”, Available: https://keras.io/guides/transfer_learning/, Accessed: 15/10/2021.
- Sidath Asiri, “Machine Learning Classifiers”, 2018, Available: https://towardsdatascience.com/machine-learning-classifiers-a5cc4e1b0623, Accessed: 15/10/2021
- Jason Brownlee, 2019, “A Gentle Introduction to the ImageNet Challenge”, Available: https://machinelearningmastery.com/introduction-to-the-imagenet-large-scale-visual-recognition-challenge-ilsvrc/, Accessed: 15/10/2021
- VijaysinhLendave, 2021, “What is Convolutional Layer?”, Available: https://analyticsindiamag.com/what-is-a-convolutional-layer/, Accessed: 15/10/2021
- Jason Brownlee, 2019, “A Gentle Introduction to Pooling Layers for Convolutional Neural Networks”,Available:https://machinelearningmastery.com/pooling-layers-for-convolutional-neural-networks/#:~:text=A%20pooling%20layer%20is%20a,Convolutional%20Layer, Accessed: 15/10/2021
- Pooja Mahajan, 2020, “Fully connected vs ConvolutionalLayer”, Available:https://medium.com/swlh/fully-connected-vs-convolutional-neural-networks-813ca7bc6ee5, Accessed: 15/10/2021
- JiwonJeong, 2019, “The Most Intuitive and Easiest Guide for Convolutional Neural Network”, Available: https://towardsdatascience.com/the-most-intuitive-and-easiest-guide-for-convolutional-neural-network-3607be47480#:~:text=Flattening%20is%20converting%20the%20data,called%20a%20fully%2Dconnected%20layer, Accessed: 15/10/2021
- Amar Budhiraja, 2016, “Dropout in (Deep) Machine Learning”,Available: https://medium.com/@amarbudhiraja/https-medium-com-amarbudhiraja-learning-less-to-learn-better-dropout-in-deep-machine-learning-74334da4bfc5, Accessed: 16/10/2021
- Jason Brownlee, 2019, “A Gentle Introduction to the Rectified Linear Unit (ReLU)”, Available: https://machinelearningmastery.com/rectified-linear-activation-function-for-deep-learning-neural-networks/, Accessed: 16/10/2021
- Kiprono Elijah Koech, 2020, “Softmax Activation Function- How It Actually Works”, Available: https://towardsdatascience.com/softmax-activation-function-how-it-actually-works-d292d335bd78, Accessed: 16/10/2021
- Keyur Rathod, 2018, “Face Detection”, Available: https://github.com/keyurr2/face-detection, Accessed :18/04/2022.
Downloads
Published
Issue
Section
License
Copyright (c) IJSRCSEIT
This work is licensed under a Creative Commons Attribution 4.0 International License.