An efficient face mask detection model for real-time applications

dc.contributor.authorOliinyk, V.
dc.contributor.authorRyzhiy, A.
dc.date.accessioned2023-02-17T10:32:02Z
dc.date.available2023-02-17T10:32:02Z
dc.date.issued2022
dc.description.abstractenRecent COVID-19 pandemic demonstrates increasing importance of facemasks and other protective equipment raising demand for specialized monitoring and control systems. In this paper, we propose an efficient and reliable method based on Dual Shot Face Detector in order to address the problem of the masked and non-masked face recognition process. The main goal of the research is to locate people without a facemask and this task combines both finding faces and facemask recognition. In addition, multiple faces can be tracked in real-time on a video stream. Experimental results show high detection performance with Mean Average Precision of 90%. Proposed solution is stable to the change of face positions, rotations and inclines. It also allows controlling correct placement of a mask on a face. In addition, different feature encoders were studied to find the balance between accuracy and inference time that is important for real-time performance with different hardware.uk
dc.format.pagerangeС. 54-64uk
dc.identifier.citationOliinyk, V. An efficient face mask detection model for real-time applications / V. Oliinyk, A. Ryzhiy // Адаптивні системи автоматичного управління : міжвідомчий науково-технічний збірник. – 2022. – № 1 (40). – С. 54-64. – Бібліогр.: 13 назв.uk
dc.identifier.doihttps://doi.org/10.20535/1560-8956.40.2022.261649
dc.identifier.urihttps://ela.kpi.ua/handle/123456789/52726
dc.language.isoenuk
dc.publisherКПІ ім. Ігоря Сікорськогоuk
dc.publisher.placeКиївuk
dc.sourceАдаптивні системи автоматичного управління : міжвідомчий науково-технічний збірник, 2022, № 1 (40)uk
dc.subjectfacemask detectionuk
dc.subjectDual Shot Face Detectoruk
dc.subjectobject detectionuk
dc.subjectreal-time systemsuk
dc.subjectcomputer visionuk
dc.subject.udc004.852uk
dc.titleAn efficient face mask detection model for real-time applicationsuk
dc.typeArticleuk

Файли

Контейнер файлів
Зараз показуємо 1 - 1 з 1
Вантажиться...
Ескіз
Назва:
ASAU_2022_1_p54-64.pdf
Розмір:
643.82 KB
Формат:
Adobe Portable Document Format
Опис:
Ліцензійна угода
Зараз показуємо 1 - 1 з 1
Ескіз недоступний
Назва:
license.txt
Розмір:
9.1 KB
Формат:
Item-specific license agreed upon to submission
Опис: