{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T17:47:43Z","timestamp":1754156863250,"version":"3.41.2"},"reference-count":32,"publisher":"Emerald","issue":"1","license":[{"start":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:00:00Z","timestamp":1656374400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.emerald.com\/insight\/site-policies"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["DTA"],"published-print":{"date-parts":[[2023,3,17]]},"abstract":"<jats:sec><jats:title content-type=\"abstract-subheading\">Purpose<\/jats:title><jats:p>This work aims to present a deep learning model for face mask detection in surveillance environments such as automatic teller machines (ATMs), banks, etc. to identify persons wearing face masks. In surveillance environments, complete visibility of the face area is a guideline, and criminals and law offenders commit crimes by hiding their faces behind a face mask. The face mask detector model proposed in this work can be used as a tool and integrated with surveillance cameras in autonomous surveillance environments to identify and catch law offenders and criminals.<\/jats:p><\/jats:sec><jats:sec><jats:title content-type=\"abstract-subheading\">Design\/methodology\/approach<\/jats:title><jats:p>The proposed face mask detector is developed by integrating the residual network (ResNet)34 feature extractor on top of three You Only Look Once (YOLO) detection layers along with the usage of the spatial pyramid pooling (SPP) layer to extract a rich and dense feature map. Furthermore, at the training time, data augmentation operations such as Mosaic and MixUp have been applied to the feature extraction network so that it can get trained with images of varying complexities. The proposed detector is trained and tested over a custom face mask detection dataset consisting of 52,635 images. For validation, comparisons have been provided with the performance of YOLO v1, v2, tiny YOLO v1, v2, v3 and v4 and other benchmark work present in the literature by evaluating performance metrics such as precision, recall, F1 score, mean average precision (mAP) for the overall dataset and average precision (AP) for each class of the dataset.<\/jats:p><\/jats:sec><jats:sec><jats:title content-type=\"abstract-subheading\">Findings<\/jats:title><jats:p>The proposed face mask detector achieved 4.75\u20139.75 per cent higher detection accuracy in terms of mAP, 5\u201331 per cent higher AP for detection of faces with masks and, specifically, 2\u201330 per cent higher AP for detection of face masks on the face region as compared to the tested baseline variants of YOLO. Furthermore, the usage of the ResNet34 feature extractor and SPP layer in the proposed detection model reduced the training time and the detection time. The proposed face mask detection model can perform detection over an image in 0.45 s, which is 0.2\u20130.15 s lesser than that for other tested YOLO variants, thus making the proposed detection model perform detections at a higher speed.<\/jats:p><\/jats:sec><jats:sec><jats:title content-type=\"abstract-subheading\">Research limitations\/implications<\/jats:title><jats:p>The proposed face mask detector model can be utilized as a tool to detect persons with face masks who are a potential threat to the automatic surveillance environments such as ATMs, banks, airport security checks, etc. The other research implication of the proposed work is that it can be trained and tested for other object detection problems such as cancer detection in images, fish species detection, vehicle detection, etc.<\/jats:p><\/jats:sec><jats:sec><jats:title content-type=\"abstract-subheading\">Practical implications<\/jats:title><jats:p>The proposed face mask detector can be integrated with automatic surveillance systems and used as a tool to detect persons with face masks who are potential threats to ATMs, banks, etc. and in the present times of COVID-19 to detect if the people are following a COVID-appropriate behavior of wearing a face mask or not in the public areas.<\/jats:p><\/jats:sec><jats:sec><jats:title content-type=\"abstract-subheading\">Originality\/value<\/jats:title><jats:p>The novelty of this work lies in the usage of the ResNet34 feature extractor with YOLO detection layers, which makes the proposed model a compact and powerful convolutional neural-network-based face mask detector model. Furthermore, the SPP layer has been applied to the ResNet34 feature extractor to make it able to extract a rich and dense feature map. The other novelty of the present work is the implementation of Mosaic and MixUp data augmentation in the training network that provided the feature extractor with 3\u00d7 images of varying complexities and orientations and further aided in achieving higher detection accuracy. The proposed model is novel in terms of extracting rich features, performing augmentation at the training time and achieving high detection accuracy while maintaining the detection speed.<\/jats:p><\/jats:sec>","DOI":"10.1108\/dta-02-2022-0076","type":"journal-article","created":{"date-parts":[[2022,7,6]],"date-time":"2022-07-06T11:55:53Z","timestamp":1657108553000},"page":"84-107","source":"Crossref","is-referenced-by-count":2,"title":["A cascaded deep-learning-based model for face mask detection"],"prefix":"10.1108","volume":"57","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7734-9946","authenticated-orcid":false,"given":"Akhil","family":"Kumar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"140","published-online":{"date-parts":[[2022,6,28]]},"reference":[{"first-page":"1850","article-title":"Optimizing expected intersection-over-union with candidate-constrained CRFs","year":"2016","key":"key2023031608343059900_ref001"},{"article-title":"Coronavirus masks a boon for crooks who hide their faces","volume-title":"AP News","year":"2020","key":"key2023031608343059900_ref002"},{"journal-title":"arXiv","article-title":"YOLOv4: optimal speed and accuracy of object detection","year":"2020","key":"key2023031608343059900_ref003"},{"key":"key2023031608343059900_ref004","doi-asserted-by":"crossref","first-page":"795","DOI":"10.1016\/j.jvcir.2018.08.016","article-title":"Face-mask recognition for fraud prevention using Gaussian mixture model","volume":"55","year":"2018","journal-title":"Journal of Visual Communication and Image Representation"},{"article-title":"Masks make it more difficult for police to identify suspects","volume-title":"WCAX3","year":"2021","key":"key2023031608343059900_ref005"},{"first-page":"426","article-title":"Detecting masked faces in the wild with LLECNNs","year":"2017","key":"key2023031608343059900_ref006"},{"key":"key2023031608343059900_ref007","doi-asserted-by":"publisher","DOI":"10.1016\/j.matpr.2021.07.368","article-title":"Novel face mask detection technique using machine learning to control COVID'19 pandemic","year":"2021","journal-title":"Materials Today: Proceedings"},{"issue":"2","key":"key2023031608343059900_ref008","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1016\/j.eij.2017.10.001","article-title":"The detection of spoofing by 3D mask in a 2D identity recognition system","volume":"19","year":"2018","journal-title":"Egyptian Informatics Journal"},{"journal-title":"arXiv","article-title":"Spatial pyramid pooling in deep convolutional networks for visual recognition","year":"2015","key":"key2023031608343059900_ref009"},{"first-page":"770","article-title":"Deep residual learning for image recognition","year":"2016","key":"key2023031608343059900_ref010"},{"issue":"3","key":"key2023031608343059900_ref011","first-page":"100035","article-title":"Face mask recognition system using CNN model","volume":"2","year":"2021","journal-title":"Neuroscience Informatics"},{"key":"key2023031608343059900_ref012","doi-asserted-by":"crossref","first-page":"103216","DOI":"10.1016\/j.bspc.2021.103216","article-title":"CNN-based bi-directional and directional long-short term memory network for determination of face mask","volume":"71","year":"2022","journal-title":"Biomedical Signal Processing and Control"},{"first-page":"247","article-title":"Real-time face mask detector using convolutional neural networks amidst COVID-19 pandemic","year":"2021","key":"key2023031608343059900_ref013"},{"key":"key2023031608343059900_ref014","doi-asserted-by":"crossref","first-page":"166744","DOI":"10.1016\/j.ijleo.2021.166744","article-title":"Scaling up face masks detection with YOLO on a novel dataset","volume":"239","year":"2021","journal-title":"Optik"},{"key":"key2023031608343059900_ref015","first-page":"102600","article-title":"Fighting against COVID-19: a novel deep learning model based on YOLO-v2 with ResNet-50 for medical face mask detection","volume":"65","year":"2020","journal-title":"Sustainable Cities and Societies"},{"key":"key2023031608343059900_ref016","doi-asserted-by":"crossref","first-page":"108288","DOI":"10.1016\/j.measurement.2020.108288","article-title":"A hybrid deep transfer learning model with machine learning methods for face mask detection in the era of the COVID-19 pandemic","volume":"167","year":"2021","journal-title":"Measurement"},{"key":"key2023031608343059900_ref017","doi-asserted-by":"crossref","first-page":"102692","DOI":"10.1016\/j.scs.2020.102692","article-title":"SSDMNV2: a real time DNN-based face mask detection system using single shot multibox detector and MobileNet v2","volume":"66","year":"2021","journal-title":"Sustainable Cities and Societies"},{"key":"key2023031608343059900_ref018","doi-asserted-by":"crossref","first-page":"457","DOI":"10.1016\/j.jvcir.2018.07.001","article-title":"Learning an video frame-based face detection system for security fields","volume":"55","year":"2018","journal-title":"Journal of Visual Communication and Image Representation"},{"first-page":"548","article-title":"Optimal decisions from probabilistic models: the intersection-over-union case","year":"2014","key":"key2023031608343059900_ref019"},{"issue":"27","key":"key2023031608343059900_ref020","doi-asserted-by":"publisher","DOI":"10.1007\/s42979-021-00894-0","article-title":"An automatic system to monitor the physical distance and face mask wearing of construction workers in COVID-19 pandemic","volume":"3","year":"2022","journal-title":"SN Computer Science"},{"journal-title":"arXiv","article-title":"YOLO9000: better, faster, stronger","year":"2016","key":"key2023031608343059900_ref021"},{"journal-title":"arXiv","article-title":"YOLOv3: an incremental improvement","year":"2018","key":"key2023031608343059900_ref022"},{"journal-title":"arXiv","article-title":"You only look once: unified, real-time object detection","year":"2015","key":"key2023031608343059900_ref023"},{"key":"key2023031608343059900_ref024","doi-asserted-by":"crossref","first-page":"509","DOI":"10.1007\/s41403-020-00157-z","article-title":"MOXA: a deep learning based unmanned approach for real-time monitoring of people wearing medical masks","volume":"5","year":"2020","journal-title":"Transactions of the Indian National Academy of Engineering"},{"key":"key2023031608343059900_ref025","doi-asserted-by":"crossref","first-page":"19753","DOI":"10.1007\/s11042-021-10711-8","article-title":"Face mask detection using YOLOv3 and faster R-CNN models: COVID-19 environment","volume":"80","year":"2021","journal-title":"Multimedia Tools and Applications"},{"article-title":"Coronavirus bandits? 2 armed men in surgical masks rob racetrack","volume-title":"The New York Times","year":"2020","key":"key2023031608343059900_ref026"},{"issue":"3","key":"key2023031608343059900_ref027","first-page":"4475","article-title":"Face mask detection and classification via deep transfer learning","volume":"81","year":"2021","journal-title":"Multimedia Tools and Applications"},{"first-page":"146","article-title":"Real-time face mask detector using YOLOv3 algorithm and Haar Cascade classifier","year":"2020","key":"key2023031608343059900_ref028"},{"issue":"3","key":"key2023031608343059900_ref029","first-page":"593","article-title":"The mask detection technology for occluded face analysis in the surveillance system","volume":"50","year":"2005","journal-title":"Journal of Forensic Science"},{"key":"key2023031608343059900_ref030","doi-asserted-by":"crossref","first-page":"104341","DOI":"10.1016\/j.imavis.2021.104341","article-title":"FMD-Yolo: an efficient face mask detection method for COVID-19 prevention and control in public","volume":"117","year":"2022","journal-title":"Image and Vision Computing"},{"key":"key2023031608343059900_ref031","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1016\/j.patrec.2017.09.011","article-title":"Fast and robust occluded face detection in ATM surveillance","volume":"107","year":"2018","journal-title":"Pattern Recognition Letters"},{"first-page":"12993","article-title":"Distance-IoU Loss: faster and better learning for bounding box regression","year":"2020","key":"key2023031608343059900_ref032"}],"container-title":["Data Technologies and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/DTA-02-2022-0076\/full\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/DTA-02-2022-0076\/full\/html","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T23:14:58Z","timestamp":1753398898000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.emerald.com\/dta\/article\/57\/1\/84-107\/26278"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,28]]},"references-count":32,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2022,6,28]]},"published-print":{"date-parts":[[2023,3,17]]}},"alternative-id":["10.1108\/DTA-02-2022-0076"],"URL":"https:\/\/doi.org\/10.1108\/dta-02-2022-0076","relation":{},"ISSN":["2514-9288","2514-9288"],"issn-type":[{"type":"print","value":"2514-9288"},{"type":"electronic","value":"2514-9288"}],"subject":[],"published":{"date-parts":[[2022,6,28]]}}}