Approaching transfer learning to identify correctly worn facial masks

This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2021.

書目詳細資料
Main Authors:	Sadid, Tausif, Hossain, Md Sadik, Sengupta, Sudip Kumar, Khondaker, Serazam Munira
其他作者:	Chakrabarty, Amitabha
格式:	Thesis
語言:	English
出版:	Brac University 2021
主題:	COVID-19 Machine Learning Deep Neural Network Climate Change Image Data Face Masks ResNet50 Inception v3 MobileNet v2 Softmax SVM
在線閱讀:	http://hdl.handle.net/10361/15205

id	10361-15205
record_format	dspace
spelling	10361-152052024-08-21T05:24:55Z Approaching transfer learning to identify correctly worn facial masks Sadid, Tausif Hossain, Md Sadik Sengupta, Sudip Kumar Khondaker, Serazam Munira Chakrabarty, Amitabha Reza, Tanzim Department of Computer Science and Engineering, Brac University COVID-19 Machine Learning Deep Neural Network Climate Change Image Data Face Masks ResNet50 Inception v3 MobileNet v2 Softmax SVM Climate Change This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2021. Cataloged from PDF version of thesis. Includes bibliographical references (page 50-53). Climate change has made the outbreak of diseases, especially airborne and contagious diseases much more extreme. Therefore, wearing masks has become essential in protecting ourselves not only from very common airborne diseases like cold, ﬂu but also from very dangerous diseases like COVID-19 or similar. Wearing face masks properly would signiﬁcantly reduce the spread of most of these diseases. In our research, we would like to propose a way to distinguish whether people are wearing facemasks properly or not by using image data. The data-set we collected included roughly 6000 images of people wearing masks both correctly and incorrectly, among which roughly 50% of it is collected locally from Bangladesh and the rest from other countries around the globe. The idea is to detect properly masked faces from images using diﬀerent Deep Neural Network architectures. Throughout our analysis, we have implemented three models, ResNet50, Inception v3, and MobileNet v2 while comparing the results when SVM is used as a classiﬁer and when Softmax is used in place of it. The results emerged with ResNet50 with an SVM classiﬁer bringing out the best results by reaching an accuracy of 97.41% accuracy making the model highly reliable and stand out from the rest. This research aims to provide a better understanding of all the models and their architectures while providing statistical results from our data-set when these models are being used to distinguish between pictures of a properly masked person and that of an improperly masked. Tausif Sadid Md Sadik Hossain Sudip Kumar Sengupta Serazam Munira Khondaker B.Sc in Computer Science 2021-10-11T06:05:08Z 2021-10-11T06:05:08Z 2021 2021-06 Thesis ID 17101083 ID 17101387 ID 17301105 ID 17101066 http://hdl.handle.net/10361/15205 en Brac University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. 53 pages application/pdf Brac University
institution	Brac University
collection	Institutional Repository
language	English
topic	COVID-19 Machine Learning Deep Neural Network Climate Change Image Data Face Masks ResNet50 Inception v3 MobileNet v2 Softmax SVM Climate Change
spellingShingle	COVID-19 Machine Learning Deep Neural Network Climate Change Image Data Face Masks ResNet50 Inception v3 MobileNet v2 Softmax SVM Climate Change Sadid, Tausif Hossain, Md Sadik Sengupta, Sudip Kumar Khondaker, Serazam Munira Approaching transfer learning to identify correctly worn facial masks
description	This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2021.
author2	Chakrabarty, Amitabha
author_facet	Chakrabarty, Amitabha Sadid, Tausif Hossain, Md Sadik Sengupta, Sudip Kumar Khondaker, Serazam Munira
format	Thesis
author	Sadid, Tausif Hossain, Md Sadik Sengupta, Sudip Kumar Khondaker, Serazam Munira
author_sort	Sadid, Tausif
title	Approaching transfer learning to identify correctly worn facial masks
title_short	Approaching transfer learning to identify correctly worn facial masks
title_full	Approaching transfer learning to identify correctly worn facial masks
title_fullStr	Approaching transfer learning to identify correctly worn facial masks
title_full_unstemmed	Approaching transfer learning to identify correctly worn facial masks
title_sort	approaching transfer learning to identify correctly worn facial masks
publisher	Brac University
publishDate	2021
url	http://hdl.handle.net/10361/15205
work_keys_str_mv	AT sadidtausif approachingtransferlearningtoidentifycorrectlywornfacialmasks AT hossainmdsadik approachingtransferlearningtoidentifycorrectlywornfacialmasks AT senguptasudipkumar approachingtransferlearningtoidentifycorrectlywornfacialmasks AT khondakerserazammunira approachingtransferlearningtoidentifycorrectlywornfacialmasks
_version_	1814309707491311616

Approaching transfer learning to identify correctly worn facial masks

相似書籍