Face mask identification with enhanced cuckoo optimization and deep learning-based faster regional neural network

Abstract A mask identification and social distance monitoring system using Unmanned Aerial Vehicles (UAV) in the outdoors has been proposed for a health establishment. The above approach performed surveillance of the surrounding area using cameras installed in UAVs and internet of things technologie...

Full description

Saved in:
Bibliographic Details
Main Authors: Binay Kumar Pandey, Digvijay Pandey, Mesfin Esayas Lelisho
Format: Article
Language:English
Published: Nature Portfolio 2024-11-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-024-78746-z
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846147720491827200
author Binay Kumar Pandey
Digvijay Pandey
Mesfin Esayas Lelisho
author_facet Binay Kumar Pandey
Digvijay Pandey
Mesfin Esayas Lelisho
author_sort Binay Kumar Pandey
collection DOAJ
description Abstract A mask identification and social distance monitoring system using Unmanned Aerial Vehicles (UAV) in the outdoors has been proposed for a health establishment. The above approach performed surveillance of the surrounding area using cameras installed in UAVs and internet of things technologies, and the captured images seem useful for tracking the entire environment. However, innate images from unmanned aerial vehicles show an adaptable visual effect in an uncontrolled environment, making face-mask detection and recognition harder. The UAV picture first had to be converted to grayscale, then its contrast was amplified. Image contrast was improved using Optimum Wavelet-Based Masking and the Enhanced Cuckoo Methodology (ECM). According to the contrast-enhanced image, Gabor-Transform (GT) and Stroke Width Transform (SWT) methods are used to derive attributes that help categorise mask-wearers and non-mask-wearers. Using the retrieved attributes, a Weighted Naive Bayes Classification (WNBC) detected masks in the images. Additionally, a deep neural network-based, the faster Region-Based Convolutional Neural Networks (R-CNN) algorithm combined with Adaptive Galactic Swarm Optimization (AGSO) is being used to identify appropriate and incorrect face mask wear in images, as well as to monitor social distancing among individuals in crowded areas. When the system recognises unmasked individuals, it sends their information to the doctor and the nearby police station. One unmanned aerial vehicle’s automated system alert people via speakers, ensuring social spacing. The problem involves a large percentage of appropriate and incorrect face mask wear using data from GitHub and Kaggle, including a training repository of 16,000 images and a testing data set of 12,751 images. To enhance the performance of the model’s learning, the methodology of 10-fold cross-validation will be used. Precision, recall, F1-score, and speed are then measured to determine the efficacy of the suggested approach.
format Article
id doaj-art-0c40b135c4a748639cd3632392cdd65d
institution Kabale University
issn 2045-2322
language English
publishDate 2024-11-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-0c40b135c4a748639cd3632392cdd65d2024-12-01T12:27:02ZengNature PortfolioScientific Reports2045-23222024-11-0114111810.1038/s41598-024-78746-zFace mask identification with enhanced cuckoo optimization and deep learning-based faster regional neural networkBinay Kumar Pandey0Digvijay Pandey1Mesfin Esayas Lelisho2Department of Information Technology, College of Technology, Govind Ballabh Pant University of Agriculture and Technology PantnagarDepartment of Technical EducationDepartment of Statistics, College of Natural and Computational Science, Mizan-Tepi UniversityAbstract A mask identification and social distance monitoring system using Unmanned Aerial Vehicles (UAV) in the outdoors has been proposed for a health establishment. The above approach performed surveillance of the surrounding area using cameras installed in UAVs and internet of things technologies, and the captured images seem useful for tracking the entire environment. However, innate images from unmanned aerial vehicles show an adaptable visual effect in an uncontrolled environment, making face-mask detection and recognition harder. The UAV picture first had to be converted to grayscale, then its contrast was amplified. Image contrast was improved using Optimum Wavelet-Based Masking and the Enhanced Cuckoo Methodology (ECM). According to the contrast-enhanced image, Gabor-Transform (GT) and Stroke Width Transform (SWT) methods are used to derive attributes that help categorise mask-wearers and non-mask-wearers. Using the retrieved attributes, a Weighted Naive Bayes Classification (WNBC) detected masks in the images. Additionally, a deep neural network-based, the faster Region-Based Convolutional Neural Networks (R-CNN) algorithm combined with Adaptive Galactic Swarm Optimization (AGSO) is being used to identify appropriate and incorrect face mask wear in images, as well as to monitor social distancing among individuals in crowded areas. When the system recognises unmasked individuals, it sends their information to the doctor and the nearby police station. One unmanned aerial vehicle’s automated system alert people via speakers, ensuring social spacing. The problem involves a large percentage of appropriate and incorrect face mask wear using data from GitHub and Kaggle, including a training repository of 16,000 images and a testing data set of 12,751 images. To enhance the performance of the model’s learning, the methodology of 10-fold cross-validation will be used. Precision, recall, F1-score, and speed are then measured to determine the efficacy of the suggested approach.https://doi.org/10.1038/s41598-024-78746-zFaster R-CNNIoTUAVOpenCV
spellingShingle Binay Kumar Pandey
Digvijay Pandey
Mesfin Esayas Lelisho
Face mask identification with enhanced cuckoo optimization and deep learning-based faster regional neural network
Scientific Reports
Faster R-CNN
IoT
UAV
OpenCV
title Face mask identification with enhanced cuckoo optimization and deep learning-based faster regional neural network
title_full Face mask identification with enhanced cuckoo optimization and deep learning-based faster regional neural network
title_fullStr Face mask identification with enhanced cuckoo optimization and deep learning-based faster regional neural network
title_full_unstemmed Face mask identification with enhanced cuckoo optimization and deep learning-based faster regional neural network
title_short Face mask identification with enhanced cuckoo optimization and deep learning-based faster regional neural network
title_sort face mask identification with enhanced cuckoo optimization and deep learning based faster regional neural network
topic Faster R-CNN
IoT
UAV
OpenCV
url https://doi.org/10.1038/s41598-024-78746-z
work_keys_str_mv AT binaykumarpandey facemaskidentificationwithenhancedcuckoooptimizationanddeeplearningbasedfasterregionalneuralnetwork
AT digvijaypandey facemaskidentificationwithenhancedcuckoooptimizationanddeeplearningbasedfasterregionalneuralnetwork
AT mesfinesayaslelisho facemaskidentificationwithenhancedcuckoooptimizationanddeeplearningbasedfasterregionalneuralnetwork