Enhancing Face Mask Detection in Public Places with Improved Yolov4 Model for Covid-19 Transmission Reduction

Muhammad Ayaz; Adnan Hameed; Said Khalid Shah; M Javed Khan; Nawaz Khan; Fouzia Idrees; Zamar Ali Shah

Authors

Muhammad Ayaz Department of Computer Science University of Science and Technology Bannu, KP, Pakistan.
Adnan Hameed Department of Computer Science University of Science and Technology Bannu, KP, Pakistan.
Said Khalid Shah Department of Computer Science University of Science and Technology Bannu, KP, Pakistan.
M Javed Khan Department of Computer Science University of Science and Technology Bannu, KP, Pakistan.
Nawaz Khan Department of Computer Science University of Science and Technology Bannu, KP, Pakistan.
Fouzia Idrees Department of Computer Science, Shaheed Benazir Bhato Women University of Peshawar, Peshawar, Khyber Pakhtunkhwa, Pakistan.
Zamar Ali Shah Department of Computer Science University of Science and Technology Bannu, KP, Pakistan.

Keywords:

COVID-19, SOPs, YOLOv4, Face masks detection, Offline-augmentation, Transfer learning, Veil images

Abstract

Over the past decade, computer vision has emerged as a pivotal field, focusing on automating systems through the interpretation of images and video frames. In response to the global impact of the COVID-19 pandemic, there has been a notable shift towards utilizing computer vision for face mask detection. Face masks, endorsed by international health authorities, play a crucial role in preventing viral transmission, prompting the development of automated monitoring systems in various public settings. However, existing artificial intelligence (AI) technologies' effectiveness diminishes in congested environments. To address this challenge, the study employs a meticulously fine-tuned YOLOv4 model for identifying instances of mask non-compliance in accordance with COVID-19 Standard Operating Procedures (SOPs). A distinctive feature of the training dataset is its inclusion of images featuring Muslim women with both half and full-face veils, considered compliant with face mask guidelines. The dataset, comprising 5800 images, including veil images from various sources, facilitated the training process, achieving a comparatively good 97.07% validation accuracy using transfer learning. The adaptations, coupled with a custom dataset featuring crowded images and advanced pre-processing techniques, enhance the model's generalization across diverse scenarios. This research significantly contributes to advancing computer vision applications, particularly in enforcing COVID-19 safety measures within public spaces. The tailored approach, involving model adjustments, underscores the adaptability of computer vision in addressing specific challenges, highlighting its potential for broader societal applications beyond the current global health crisis.

References

C. Li, J. Cao, and X. Zhang, “Robust deep learning method to detect face masks,” ACM Int. Conf. Proceeding Ser., pp. 74–77, Oct. 2020, doi: 10.1145/3421766.3421768.

“WHAT YOU NEED TO KNOW ABOUT CORONAVIRUS (COVID-19) - COVID-19 | Ministry of Health.” Accessed: Mar. 13, 2024. [Online]. Available: https://www.health.go.ug/covid/document/what-you-need-to-know-about-coronavirus-covid-19/

F. Di Gennaro et al., “Coronavirus Diseases (COVID-19) Current Status and Future Perspectives: A Narrative Review,” Int. J. Environ. Res. Public Heal. 2020, Vol. 17, Page 2690, vol. 17, no. 8, p. 2690, Apr. 2020, doi: 10.3390/IJERPH17082690.

F. M. J. Mehedi Shamrat, S. Chakraborty, M. M. Billah, M. Al Jubair, M. S. Islam, and R. Ranjan, “Face Mask Detection using Convolutional Neural Network (CNN) to reduce the spread of Covid-19,” Proc. 5th Int. Conf. Trends Electron. Informatics, ICOEI 2021, pp. 1231–1237, Jun. 2021, doi: 10.1109/ICOEI51242.2021.9452836.

M. R. Bhuiyan, S. A. Khushbu, and M. S. Islam, “A Deep Learning Based Assistive System to Classify COVID-19 Face Mask for Human Safety with YOLOv3,” 2020 11th Int. Conf. Comput. Commun. Netw. Technol. ICCCNT 2020, Jul. 2020, doi: 10.1109/ICCCNT49239.2020.9225384.

S. Balaji, B. Balamurugan, T. A. Kumar, R. Rajmohan, and P. P. Kumar, “A Brief Survey on AI Based Face Mask Detection System for Public Places.” Mar. 28, 2021. Accessed: Mar. 13, 2024. [Online]. Available: https://papers.ssrn.com/abstract=3814341

J. Redmon and A. Farhadi, “YOLO9000: Better, Faster, Stronger,” Proc. - 30th IEEE Conf. Comput. Vis. Pattern Recognition, CVPR 2017, vol. 2017-January, pp. 6517–6525, Dec. 2016, doi: 10.1109/CVPR.2017.690.

S. Jignesh Chowdary, G., Punn, N. S., Sonbhadra, S. K., & Agarwal, “Face mask detection using transfer learning of inceptionv3. In Big Data Analytics 8th International Conference, BDA 2020, Sonepat, India, December 15–18, 2020, Proceedings 8 (pp. 81-90).,” Springer Int. Publ., pp. 81–90, 2020.

B. M. et Al., “Face mask detection using convolutional neural network,” J. Nat. Remedies, vol. 21, no. 12, 2021.

M. M. Rahman, M. M. H. Manik, M. M. Islam, S. Mahmud, and J. H. Kim, “An automated system to limit COVID-19 using facial mask detection in smart city network,” IEMTRONICS 2020 - Int. IOT, Electron. Mechatronics Conf. Proc., Sep. 2020, doi: 10.1109/IEMTRONICS51293.2020.9216386.

G. Yang et al., “Face Mask Recognition System with YOLOV5 Based on Image Recognition,” 2020 IEEE 6th Int. Conf. Comput. Commun. ICCC 2020, pp. 1398–1404, Dec. 2020, doi: 10.1109/ICCC51575.2020.9345042.

B. Sathyabama, A. Devpura, M. Maroti, and R. S. Rajput, “Monitoring pandemic precautionary protocols using real-time surveillance and artificial intelligence,” Proc. 3rd Int. Conf. Intell. Sustain. Syst. ICISS 2020, pp. 1036–1041, Dec. 2020, doi: 10.1109/ICISS49785.2020.9315934.

X. Ren and X. Liu, “Mask wearing detection based on YOLOv3,” J. Phys. Conf. Ser., vol. 1678, no. 1, p. 012089, Nov. 2020, doi: 10.1088/1742-6596/1678/1/012089.

X. Jiang, T. Gao, Z. Zhu, and Y. Zhao, “Real-Time Face Mask Detection Method Based on YOLOv3,” Electron. 2021, Vol. 10, Page 837, vol. 10, no. 7, p. 837, Apr. 2021, doi: 10.3390/ELECTRONICS10070837.

S. Saponara, A. Elhanashi, and A. Gagliardi, “Implementing a real-time, AI-based, people detection and social distancing measuring system for Covid-19,” J. Real-Time Image Process., vol. 18, no. 6, pp. 1937–1947, Dec. 2021, doi: 10.1007/S11554-021-01070-6/FIGURES/11.

H. Ahmed, Abd El-Aziz & Azim, Nesrine & Mahmood, Mahmood & Alshammari, “A Deep Learning Model for Face Mask Detection,” vol. 2, pp. 101–107, 2021, doi: 10.22937/IJCSNS.2021.21.10.13.

E. Mbunge, S. Simelane, S. G. Fashoto, B. Akinnuwesi, and A. S. Metfula, “Application of deep learning and machine learning models to detect COVID-19 face masks - A review,” Sustain. Oper. Comput., vol. 2, no. August, pp. 235–245, 2021, doi: 10.1016/j.susoc.2021.08.001.

R. Laroca et al., “A Robust Real-Time Automatic License Plate Recognition Based on the YOLO Detector,” Proc. Int. Jt. Conf. Neural Networks, vol. 2018-July, Oct. 2018, doi: 10.1109/IJCNN.2018.8489629.

L. Fang et al., “Ginger Seeding Detection and Shoot Orientation Discrimination Using an Improved YOLOv4-LITE Network,” Agron. 2021, Vol. 11, Page 2328, vol. 11, no. 11, p. 2328, Nov. 2021, doi: 10.3390/AGRONOMY11112328.

S. Tenzin, P. Dorji, B. Subba, and T. Tobgay, “Smart Check-in Check-out System for Vehicles using Automatic Number Plate Recognition,” 2020 11th Int. Conf. Comput. Commun. Netw. Technol. ICCCNT 2020, no. July, 2020, doi: 10.1109/ICCCNT49239.2020.9225555.

M. Ayaz et al., “Automatic Early Diagnosis of Dome Galls in Cordia Dichotoma G. Forst. Using Deep Transfer Learning,” IEEE Access, vol. 11, pp. 59511–59523, 2023, doi: 10.1109/ACCESS.2023.3283568.

“GitHub - prajnasb/observations.” Accessed: Mar. 13, 2024. [Online]. Available: https://github.com/prajnasb/observations

“Face Mask Detection.” Accessed: Mar. 13, 2024. [Online]. Available: https://www.kaggle.com/datasets/andrewmvd/face-mask-detection

“Evaluation of data augmentation of MR images for deep learning.” Accessed: Mar. 13, 2024. [Online]. Available: https://lup.lub.lu.se/luur/download?func=downloadFile&recordOId=8952747&fileOId=8952748

S. K. Devalla et al., “A Deep Learning Approach to Denoise Optical Coherence Tomography Images of the Optic Nerve Head,” Sci. Reports 2019 91, vol. 9, no. 1, pp. 1–13, Oct. 2019, doi: 10.1038/s41598-019-51062-7.