RT info:eu-repo/semantics/article
T1 FMDNet: An efficient system for face mask detection based on lightweight model during COVID-19 pandemic in public areas
A1 Benifa, J. V. Bibal
A1 Chola, Channabasava
A1 Muaad, Abdullah Y.
A1 Hayat, Mohd Ammar Bin
A1 Bin Heyat, Md Belal
A1 Mehrotra, Rajat
A1 Akhtar, Faijan
A1 Hussein, Hany S.
A1 Ramírez Vargas, Debora Libertad
A1 Kuc Castilla, Ángel
A1 Torre Díez, Isabel de la
A1 Khan, Salabat
K1 Artificial intelligence
K1 COVID-19
K1 Machine learning
K1 Aprendizaje automático
K1 Masks
K1 Mascarillas
K1 Pandemics
K1 Pandemias
K1 SARS-CoV-2
K1 Electronic surveillance
K1 Vigilancia electrónica
K1 Public health
K1 Medicine
K1 Public health
K1 Electronic data processing
K1 Procesamiento de datos
K1 1203.04 Inteligencia Artificial
K1 32 Ciencias Médicas
K1 3212 Salud Publica
AB A new artificial intelligence-based approach is proposed by developing a deep learning (DL) model for identifying the people who violate the face mask protocol in public places. To achieve this goal, a private dataset was created, including different face images with and without masks. The proposed model was trained to detect face masks from real-time surveillance videos. The proposed face mask detection (FMDNet) model achieved a promising detection of 99.0% in terms of accuracy for identifying violations (no face mask) in public places. The model presented a better detection capability compared to other recent DL models such as FSA-Net, MobileNet V2, and ResNet by 24.03%, 5.0%, and 24.10%, respectively. Meanwhile, the model is lightweight and had a confidence score of 99.0% in a resource-constrained environment. The model can perform the detection task in real-time environments at 41.72 frames per second (FPS). Thus, the developed model can be applicable and useful for governments to maintain the rules of the SOP protocol.
PB MDPI
SN 1424-8220
YR 2023
FD 2023
LK https://uvadoc.uva.es/handle/10324/66511
UL https://uvadoc.uva.es/handle/10324/66511
LA eng
NO Sensors, 2023, Vol. 23, Nº. 13, 6090
NO Producción Científica
DS UVaDOC
RD 28-nov-2024