FMDNet: An Efficient System for Face Mask Detection Based on Lightweight Model during COVID-19 Pandemic in Public Areas

J V Bibal Benifa; Channabasava Chola; Abdullah Y Muaad; Mohd Ammar Bin Hayat; Md Belal Bin Heyat; Rajat Mehrotra; Faijan Akhtar; Hany S Hussein; Debora Libertad Ramírez Vargas; Ángel Kuc Castilla; Isabel de la Torre Díez; Salabat Khan

doi:10.3390/s23136090

FMDNet: An Efficient System for Face Mask Detection Based on Lightweight Model during COVID-19 Pandemic in Public Areas

Sensors (Basel). 2023 Jul 2;23(13):6090. doi: 10.3390/s23136090.

Authors

J V Bibal Benifa¹, Channabasava Chola¹, Abdullah Y Muaad², Mohd Ammar Bin Hayat³, Md Belal Bin Heyat⁴, Rajat Mehrotra⁵, Faijan Akhtar⁶, Hany S Hussein^{7

8}, Debora Libertad Ramírez Vargas^{9

10

11}, Ángel Kuc Castilla^{10

12

13}, Isabel de la Torre Díez¹⁴, Salabat Khan⁴

Affiliations

¹ Department of Computer Science and Engineering, Indian Institute of Information Technology Kottayam, Kottayam 686635, India.
² Department of Studies in Computer Science, Mysore University, Manasagangothri, Mysore 570006, India.
³ M.A.H. Inter College, Deoria 274408, India.
⁴ IoT Research Center, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen 518060, China.
⁵ Department of Examination and Analysis, Amity University, Noida 201303, India.
⁶ School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 610054, China.
⁷ Electrical Engineering Department, Faculty of Engineering, King Khalid University, Abha 61411, Saudi Arabia.
⁸ Electrical Engineering Department, Faculty of Engineering, Aswan University, Aswan 81528, Egypt.
⁹ Higher Polytechnic School, Universidad Europea del Atlántico, Isabel Torres, 39011 Santander, Spain.
¹⁰ Department of Engineering and Projects, Universidad Internacional Iberoamericana, Campeche 24560, Mexico.
¹¹ Facultade de Engenharias, Universidade Internacional do Cuanza, Cuito EN250, Angola.
¹² School of Engineering, Fundación Universitaria Internacional de Colombia, Bogotá 11001, Colombia.
¹³ Higher Polytechnic School, Universidad de La Romana, La Romana 22000, Dominican Republic.
¹⁴ Department of Signal Theory and Communications, University of Valladolid, 47011 Valladolid, Spain.

Abstract

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.

Keywords: COVID-19; FaceMask; MobileNetV2; SARS CoV-2; World Health Organization; artificial intelligence; deep learning; pandemic; surveillance.

MeSH terms

Artificial Intelligence
COVID-19*
Humans
Masks*
Pandemics
Personal Protective Equipment

Grants and funding

This work was supported by the Deanship of Scientific Research at King Khalid University for work through the Large Groups Project under Grant Number RGP.2/162/44.