Facial expression recognition: convolutional attentional masking network and ensemble approach

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

Podrobná bibliografie
Hlavní autoři:	Kowsar, Ibna, Zaman, Mashﬁq Shahriar, Sakib, Md. Fahmidur Rahman
Další autoři:	Kabir, Md. Hasanul
Médium:	Diplomová práce
Jazyk:	English
Vydáno:	Brac University 2021
Témata:	Facial Expression Deep Learning RAF FER2013 CAMnet Attention
On-line přístup:	http://hdl.handle.net/10361/15461

id	10361-15461
record_format	dspace
spelling	10361-154612022-01-26T10:13:21Z Facial expression recognition: convolutional attentional masking network and ensemble approach Kowsar, Ibna Zaman, Mashﬁq Shahriar Sakib, Md. Fahmidur Rahman Kabir, Md. Hasanul Ajwad, Rasif Department of Computer Science and Engineering, Brac University Facial Expression Deep Learning RAF FER2013 CAMnet Attention Deep Learning 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 (pages 45-48). Facial expression plays a signiﬁcant role in human communication. The necessity of recognizing facial expression is increasing rapidly as it can be implemented in various important ﬁelds such as in human-computer interactions, medical care, autonomous transportation systems etc. The facial expression detection has been accomplished by the analysis of convolutional neural networks on the micromotors and action units. In this thesis, we have introduced a new variant of residual architecture named CAMnet which uses the split attentional module and the masking module mechanisms simultaneously. Also, the model performs better compared to other models without using any pretrained weights on small dataset like FER2013. Additionally, along with the CAMnet an ensemble model has been implemented and we have achieved 76.12% accuracy on the FER2013 test set. Ibna Kowsar Mashﬁq Shahriar Zaman Md. Fahmidur Rahman Sakib B. Computer Science 2021-10-19T09:17:13Z 2021-10-19T09:17:13Z 2021 2021-01 Thesis ID 17301130 ID 17301167 ID 17301196 http://hdl.handle.net/10361/15461 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. 48 pages application/pdf Brac University
institution	Brac University
collection	Institutional Repository
language	English
topic	Facial Expression Deep Learning RAF FER2013 CAMnet Attention Deep Learning
spellingShingle	Facial Expression Deep Learning RAF FER2013 CAMnet Attention Deep Learning Kowsar, Ibna Zaman, Mashﬁq Shahriar Sakib, Md. Fahmidur Rahman Facial expression recognition: convolutional attentional masking network and ensemble approach
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	Kabir, Md. Hasanul
author_facet	Kabir, Md. Hasanul Kowsar, Ibna Zaman, Mashﬁq Shahriar Sakib, Md. Fahmidur Rahman
format	Thesis
author	Kowsar, Ibna Zaman, Mashﬁq Shahriar Sakib, Md. Fahmidur Rahman
author_sort	Kowsar, Ibna
title	Facial expression recognition: convolutional attentional masking network and ensemble approach
title_short	Facial expression recognition: convolutional attentional masking network and ensemble approach
title_full	Facial expression recognition: convolutional attentional masking network and ensemble approach
title_fullStr	Facial expression recognition: convolutional attentional masking network and ensemble approach
title_full_unstemmed	Facial expression recognition: convolutional attentional masking network and ensemble approach
title_sort	facial expression recognition: convolutional attentional masking network and ensemble approach
publisher	Brac University
publishDate	2021
url	http://hdl.handle.net/10361/15461
work_keys_str_mv	AT kowsaribna facialexpressionrecognitionconvolutionalattentionalmaskingnetworkandensembleapproach AT zamanmashfiqshahriar facialexpressionrecognitionconvolutionalattentionalmaskingnetworkandensembleapproach AT sakibmdfahmidurrahman facialexpressionrecognitionconvolutionalattentionalmaskingnetworkandensembleapproach
_version_	1814308232497201152

Facial expression recognition: convolutional attentional masking network and ensemble approach

Podobné jednotky