Detection of Mask Usage Using Image Processing and Convolutional Neural Network (CNN) Methods

Ervan Asri; Yance Sonatha; Indri Rahmayuni; Meri Azmi

doi:10.24036/jtip.v15i1.548

Ervan Asri Information Technology Department, Politeknik Negeri Padang
Yance Sonatha Politeknik Negeri Padang
Indri Rahmayuni Information Technology Department, Politeknik Negeri Padang
Meri Azmi Information Technology Department, Politeknik Negeri Padang

DOI: https://doi.org/10.24036/jtip.v15i1.548

Keywords: CNN, Covid-19, Deep Learning, Image Processing, Mask Detection

Abstract

Since the first case of COVID-19 was discovered in Indonesia in March 2020, the number of positively contaminated patients is increasing every day. On April 13, 2021, there were 1,571,824 patients who were positively contaminated with COVID-19. Various efforts have been made to suppress the spread of this dangerous virus, one of which is by implementing health protocols that must be obeyed when someone is in a crowd. The recommendation to use masks is a form of health protocol. Often people ignore the importance of using masks in public places, sometimes masks are used not in accordance with justified recommendations. For this reason, research is proposed which will later produce a system that can detect whether someone has used a mask correctly. The system was developed using a deep learning method using a convolutional neural network (CNN). CNN will classify data objects in the form of images / user images and determine whether they are wearing masks correctly or not. The output of the system in the form of audio will be delivered through speakers installed adjacent to the camera which will scan the user's face.

References

World Health Organization, “Looking back at a year that changed the world: WHO’s response to COVID-19,” no. January, p. 66, 2021.

S. Lin, R. Kantor, and E. Clark, “Coronavirus Disease 2019,” Clinics in Geriatric Medicine, vol. 37, no. 4, pp. 509–522, 2021, doi: 10.1016/j.cger.2021.05.001.

Kemenkes RI, “COVID 19 di Indonesia.” https://covid19.kemkes.go.id/ (accessed Jan. 27, 2022).

P. Wu, H. Li, N. Zeng, and F. Li, “FMD-Yolo: An efficient face mask detection method for COVID-19 prevention and control in public,” Image and Vision Computing, vol. 117, Jan. 2022, doi: 10.1016/j.imavis.2021.104341.

S. Sethi, M. Kathuria, and T. Kaushik, “Face mask detection using deep learning: An approach to reduce risk of Coronavirus spread,” Journal of Biomedical Informatics, vol. 120, Aug. 2021, doi: 10.1016/j.jbi.2021.103848.

B. Varshini, H. Yogesh, S. D. Pasha, M. Suhail, V. Madhumitha, and A. Sasi, “IoT-Enabled smart doors for monitoring body temperature and face mask detection,” Global Transitions Proceedings, vol. 2, no. 2, pp. 246–254, Nov. 2021, doi: 10.1016/j.gltp.2021.08.071.

M. M. Lambacing and Ferdiansyah, “Rancang Bangun New Normal Covid 19 Masker Detektor Dengan Notifikasi Telegram Berbasis Internet of Things,” Jurnal DINAMIK, vol. 25, no. 2, pp. 77–84, 2020.

N. Sharma, V. Jain, and A. Mishra, “An Analysis of Convolutional Neural Networks for Image Classification,” in Procedia Computer Science, 2018, vol. 132, pp. 377–384. doi: 10.1016/j.procs.2018.05.198.

A. Y. Wicaksono, N. Suciati, C. Fatichah, K. Uchimura, and G. Koutaki, “Modified Convolutional Neural Network Architecture for Batik Motif Image Classification,” 2017.

Prof. B. S.P., S. Kotambkar, A. Lakade, K. Mande, and T. Deshmukh, “Parking Management System using Image Processing and Distributed Approach,” IJARCCE, vol. 6, no. 3, pp. 584–586, Mar. 2017, doi: 10.17148/ijarcce.2017.63136.

L. Deng and D. Yu, “Deep learning: Methods and applications,” Foundations and Trends in Signal Processing, vol. 7, no. 3–4. Now Publishers Inc, pp. 197–387, 2013. doi: 10.1561/2000000039.

Y. Lu, “Deep neural networks and fraud detection,” Uppsala, Sweden, Oct. 2017.

I. W. Suartika E.P, A. Y. Wijaya, and R. Soelaiman, “Klasifikasi Citra Menggunakan Convolutional Neural Network (Cnn) pada Caltech 101,” Teknik ITS, vol. 5, no. 1, pp. A65–A69, 2016.

Ö. İni̇k, M. Altıok, E. Ülker, and B. Koçer, “MODE-CNN: A fast converging multi-objective optimization algorithm for CNN-based models,” Applied Soft Computing, vol. 109, Sep. 2021, doi: 10.1016/j.asoc.2021.107582.

Darmatasia, “Deteksi Penggunaan Masker Menggunakan Xception Transfer Learning,” INSTEK - Informatika Sains dan Teknologi, vol. 5, no. 2, pp. 279–288, 2020.