Deep learning-based occlusion-aware face mask detection for airborne disease control

Abstract Airborne infectious diseases are a significant threat to human beings. Nowadays, one of the deadliest airborne diseases, coronavirus (COVID-19), is resulting in a massive health crisis due to its rapid transmission. The World Health Organization for protection against the spread of airborne...

Full description

Saved in:
Bibliographic Details
Main Authors: Teshome Ayechiluhem Yalew, Sosina M. Gashaw, Aleka Melese Ayalew, Mourad Oussalah
Format: Article
Language:English
Published: Springer 2025-07-01
Series:Discover Computing
Subjects:
Online Access:https://doi.org/10.1007/s10791-025-09684-1
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849342038810558464
author Teshome Ayechiluhem Yalew
Sosina M. Gashaw
Aleka Melese Ayalew
Mourad Oussalah
author_facet Teshome Ayechiluhem Yalew
Sosina M. Gashaw
Aleka Melese Ayalew
Mourad Oussalah
author_sort Teshome Ayechiluhem Yalew
collection DOAJ
description Abstract Airborne infectious diseases are a significant threat to human beings. Nowadays, one of the deadliest airborne diseases, coronavirus (COVID-19), is resulting in a massive health crisis due to its rapid transmission. The World Health Organization for protection against the spread of airborne diseases has set several guidelines. The most effective preventive measure against airborne diseases, according to the World Health Organization, is wearing masks in public places and crowded areas. It is challenging to monitor people manually in these areas. In this study, we collect data from public and local sources to develop an occlusion-aware face mask detection model. This study presents a deep learning-based occlusion-aware face mask detection model designed to identify both proper and improper mask usage, even under partial facial occlusions. A dataset of 4,820 images, including occlusions from hands, objects, and mask misuse, was used to train and evaluate three convolutional neural network models: InceptionV3, MobileNetV2, and DenseNet121. Among them, DenseNet121 achieved the highest accuracy of 96.3% on test data. Therefore, our proposed study is used to investigate occlusion aware face mask classification using deep learning.
format Article
id doaj-art-1f14f675cd4d48fc98e1c391db4386e7
institution Kabale University
issn 2948-2992
language English
publishDate 2025-07-01
publisher Springer
record_format Article
series Discover Computing
spelling doaj-art-1f14f675cd4d48fc98e1c391db4386e72025-08-20T03:43:30ZengSpringerDiscover Computing2948-29922025-07-0128112510.1007/s10791-025-09684-1Deep learning-based occlusion-aware face mask detection for airborne disease controlTeshome Ayechiluhem Yalew0Sosina M. Gashaw1Aleka Melese Ayalew2Mourad Oussalah3Department of Information Systems, University of GondarDepartment of Electrical and Computer Engineering, Addis Ababa Institute of TechnologyCenter for Machine Vision and Signal Analysis (CMVS), University of OuluCenter for Machine Vision and Signal Analysis (CMVS), University of OuluAbstract Airborne infectious diseases are a significant threat to human beings. Nowadays, one of the deadliest airborne diseases, coronavirus (COVID-19), is resulting in a massive health crisis due to its rapid transmission. The World Health Organization for protection against the spread of airborne diseases has set several guidelines. The most effective preventive measure against airborne diseases, according to the World Health Organization, is wearing masks in public places and crowded areas. It is challenging to monitor people manually in these areas. In this study, we collect data from public and local sources to develop an occlusion-aware face mask detection model. This study presents a deep learning-based occlusion-aware face mask detection model designed to identify both proper and improper mask usage, even under partial facial occlusions. A dataset of 4,820 images, including occlusions from hands, objects, and mask misuse, was used to train and evaluate three convolutional neural network models: InceptionV3, MobileNetV2, and DenseNet121. Among them, DenseNet121 achieved the highest accuracy of 96.3% on test data. Therefore, our proposed study is used to investigate occlusion aware face mask classification using deep learning.https://doi.org/10.1007/s10791-025-09684-1COVID-19OcclusionFace maskInceptionV3MobileNetV2Airborne infectious
spellingShingle Teshome Ayechiluhem Yalew
Sosina M. Gashaw
Aleka Melese Ayalew
Mourad Oussalah
Deep learning-based occlusion-aware face mask detection for airborne disease control
Discover Computing
COVID-19
Occlusion
Face mask
InceptionV3
MobileNetV2
Airborne infectious
title Deep learning-based occlusion-aware face mask detection for airborne disease control
title_full Deep learning-based occlusion-aware face mask detection for airborne disease control
title_fullStr Deep learning-based occlusion-aware face mask detection for airborne disease control
title_full_unstemmed Deep learning-based occlusion-aware face mask detection for airborne disease control
title_short Deep learning-based occlusion-aware face mask detection for airborne disease control
title_sort deep learning based occlusion aware face mask detection for airborne disease control
topic COVID-19
Occlusion
Face mask
InceptionV3
MobileNetV2
Airborne infectious
url https://doi.org/10.1007/s10791-025-09684-1
work_keys_str_mv AT teshomeayechiluhemyalew deeplearningbasedocclusionawarefacemaskdetectionforairbornediseasecontrol
AT sosinamgashaw deeplearningbasedocclusionawarefacemaskdetectionforairbornediseasecontrol
AT alekameleseayalew deeplearningbasedocclusionawarefacemaskdetectionforairbornediseasecontrol
AT mouradoussalah deeplearningbasedocclusionawarefacemaskdetectionforairbornediseasecontrol