Comparative evaluation of deep learning methods for masked face recognition

The thesis presents methods for improving the efficiency and accuracy of masked face recognition systems, which have become increasingly important in the aftermath of the COVID-19 pandemicThree different methods are proposed and evaluated, namely CNNSVM, PRFCNN, and HRNN. The CNNSVM method combines...

Full description

Saved in:

Bibliographic Details
Main Author:	Chong, Lucas Wei Jie
Format:	Thesis
Published:	2023
Subjects:	QA71-90 Instruments and machines
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-mmu-ep.12869
record_format	uketd_dc
spelling	my-mmu-ep.128692024-08-28T03:56:53Z Comparative evaluation of deep learning methods for masked face recognition 2023-08 Chong, Lucas Wei Jie QA71-90 Instruments and machines The thesis presents methods for improving the efficiency and accuracy of masked face recognition systems, which have become increasingly important in the aftermath of the COVID-19 pandemicThree different methods are proposed and evaluated, namely CNNSVM, PRFCNN, and HRNN. The CNNSVM method combines CNNs and SVMs to extract features and classify masked face images, whereas the PRFCNN method enhances this process by incorporating a random forest, PCA and CNN. The HRNN method utilizes a recurrent neural network to improve the recognition of masked faces.. The proposed methods are evaluated and compared against several state-of-the-art approaches using the RMFD and LFW-SMFD benchmark datasets. The results show that all three methods outperform the existing methods in terms of accuracy, especially when high mask coverage is used.. The CNNSVM method achieved an accuracy of 98.39% on the RMFD dataset, outperforming the state-of-the-art methods. The PRFCNN method achieved an accuracy of 99% on the benchmark dataset, indicating the effectiveness of incorporating a random forest in the feature extraction process. The HRNN method, which leverages the temporal information in the masked face images, achieved a TAR of 99% on both benchmark datasets, demonstrating the potential of recurrent neural networks for masked face recognition. 2023-08 Thesis https://shdl.mmu.edu.my/12869/ http://erep.mmu.edu.my/ masters Multimedia University Faculty of Information Science and Technology (FIST) EREP ID: 12293
institution	Multimedia University
collection	MMU Institutional Repository
topic	QA71-90 Instruments and machines
spellingShingle	QA71-90 Instruments and machines Chong, Lucas Wei Jie Comparative evaluation of deep learning methods for masked face recognition
description	The thesis presents methods for improving the efficiency and accuracy of masked face recognition systems, which have become increasingly important in the aftermath of the COVID-19 pandemicThree different methods are proposed and evaluated, namely CNNSVM, PRFCNN, and HRNN. The CNNSVM method combines CNNs and SVMs to extract features and classify masked face images, whereas the PRFCNN method enhances this process by incorporating a random forest, PCA and CNN. The HRNN method utilizes a recurrent neural network to improve the recognition of masked faces.. The proposed methods are evaluated and compared against several state-of-the-art approaches using the RMFD and LFW-SMFD benchmark datasets. The results show that all three methods outperform the existing methods in terms of accuracy, especially when high mask coverage is used.. The CNNSVM method achieved an accuracy of 98.39% on the RMFD dataset, outperforming the state-of-the-art methods. The PRFCNN method achieved an accuracy of 99% on the benchmark dataset, indicating the effectiveness of incorporating a random forest in the feature extraction process. The HRNN method, which leverages the temporal information in the masked face images, achieved a TAR of 99% on both benchmark datasets, demonstrating the potential of recurrent neural networks for masked face recognition.
format	Thesis
qualification_level	Master's degree
author	Chong, Lucas Wei Jie
author_facet	Chong, Lucas Wei Jie
author_sort	Chong, Lucas Wei Jie
title	Comparative evaluation of deep learning methods for masked face recognition
title_short	Comparative evaluation of deep learning methods for masked face recognition
title_full	Comparative evaluation of deep learning methods for masked face recognition
title_fullStr	Comparative evaluation of deep learning methods for masked face recognition
title_full_unstemmed	Comparative evaluation of deep learning methods for masked face recognition
title_sort	comparative evaluation of deep learning methods for masked face recognition
granting_institution	Multimedia University
granting_department	Faculty of Information Science and Technology (FIST)
publishDate	2023
_version_	1811768012832768000

Comparative evaluation of deep learning methods for masked face recognition

Similar Items