Convolutional Neural Network for the Classification of Images of People Using PPE-Type Masks

• Pedro Henrile Salvador IFCE
• André Luis ALbuquerque Pinheiro IFCE
• Francisco Cleber da Conceição Feitosa UFPI
• Robson Gonçalves Fechine Feitosa IFCE

DOI: https://doi.org/10.5753/ercemapi.2024.243567

Abstract

The present work used Computer Vision and Convolutional Neural Network (CNN) techniques, with the aim of classifying images of people using or not using PPE (Personal Protective Equipment) masks. To this end, an image repository was sought for training, validation and testing; LabelImg was used to label the training images, and CNN was used to build the model. After several experiments, the best results obtained were Accuracy of 1.0, Coverage of 0.88 and F-Measure of 0.93.

References

Ari, N. and Ustazhanov, M. (2014). Matplotlib in python. In 2014 11th International Conference on Electronics, Computer and Computation (ICECCO), pages 1–6. IEEE.

Balasundaram, A., Kumar, N., Sivaraman, A. K., Vincent, R., and Rajesh, M. (2021).

Mask detection in crowded environment using machine learning. In 2021 2nd International Conference on Smart Electronics and Communication (ICOSEC), pages 1202–1206. IEEE.

Floriano, I., Silvinato, A., Bacha, H. A., Barbosa, A. N., Tanni, S., & Bernardo, W. M. (2024). Eficácia do uso de máscaras durante o surto de COVID-19 em estudos de coorte e caso-controle: uma revisão sistemática e meta-análise. Jornal Brasileiro de Pneumologia, 49, e20230003.

Gavai, N. R., Jakhade, Y. A., Tribhuvan, S. A., and Bhattad, R. (2017). Mobilenets for flower classification using tensorflow. In 2017 international conference on big data, IoT and data science (BID), pages 154–158. IEEE.

Goldsborough, P. (2016). A tour of tensorflow. arXiv preprint arXiv:1610.01178.

Jaime, T. F. (2020). Uso de algoritmos de aprendizado de máquina supervisionado para rotulação de dados.

Kähler, C. J., and Hain, R. (2020). Fundamental protective mechanisms of face masks against droplet infections. Journal of aerosol science, 148, 105617. DOI: 10.1016/j.jaerosci.2020.105617

Lodh, A., Saxena, U., Motwani, A., Shakkeera, L., Sharmasth, V. Y., et al. (2020). Prototype for integration of face mask detection and person identification model–covid-19. In 2020 4th International Conference on Electronics, Communication and Aerospace Technology (ICECA), pages 1361–1367. IEEE.

Schutze, H., Manning, C. D., and Raghavan, P. (2008). Introduction to information retrieval, volume 39. Cambridge University Press Cambridge.

Corrêa, G. P., Colombini, E. L., Técnico-IC-PFG, R., & de Graduação, P. F. (2023). Aumento de dados com modelos de difusão image to image e GANs para melhoria na generalização de detectores de deepfake.

Shorten, C. and Khoshgoftaar, T. M. (2019). A survey on image data augmentation for deep learning. Journal of big data, 6(1):1–48.

Suganthalakshmi, R., Hafeeza, A., Abinaya, P., and Devi, A. G. (2021). Covid-19 face-mask detection with deep learning and computer vision. Int. J. Eng. Res. Tech.(IJERT) ICRADL.

UBAI(2023). Best data augmentation techniques [2024 update]. Disponível em: [link]. Acesso em: 9 jul. 2024.

TensorFlow (2022). Load and preprocess data. Acessado: 2024-04-05.

Vrigkas, M., Kourfalidou, E.-A., Plissiti, M. E., and Nikou, C. (2022). Facemask: A new image dataset for the automated identification of people wearing masks in the wild. Sensors, 22(3):896.

Who, W. H. O. (2024). Coronavirus disease (covid-19) outbreak situation. Disponível em: [link]. Acesso em: 09 jul. 2024.

Ying, X. (2019, February). An overview of overfitting and its solutions. In Journal of physics: Conference series (Vol. 1168, p. 022022). IOP Publishing.