Mask detection for COVID-19 through of Deep Learning using OpenCV and Cascade Trainer GUI
DOI:
https://doi.org/10.26423/rctu.v8i1.572Keywords:
Machine Learning, Deep Learning, convolutional networks, false positivesAbstract
The covid-19 pandemic caused a health crisis worldwide, one of the recommendations of scientists and governments to avoid contagion is the use of a mask, therefore this article was focused on which software is developed that allows the mask to be detected in different scenarios using the Python programming language through the cv2, os, numpy and imutils libraries, using convolutional neural networks that are more efficient than common neural networks, which were trained with the Cascade Trainer GUI software, using Different amounts of databases from 400 to 1400 images to compare different types of mask detection system accuracy. However, the first database did not obtain a good pressure due to a low number of false positives, so as more data is used, the precision increased considerably until obtaining a precision of 92% with a mask and a 100% no mask.
Downloads
References
Andrés, J. M. A., de Castro, M. T. G. V., Vicente-Guijarro, J., Peribáñez, J. B., Haro, M. G., Valencia-Martín, J. L., ... & Montero, G. G. (2020). Mascarillas como equipo de protección individual durante la pandemia de COVID-19: cómo, cuándo y cuáles deben utilizarse. Journal of Healthcare Quality Research, 35(4), 245-252. DOI: https://doi.org/10.1016/j.jhqr.2020.06.001
Loey, M., Manogaran, G., Taha, M. H. N., & Khalifa, N. E. M. (2021). A hybrid deep transfer learning model with Machine Learning methods for face mask detection in the era of the COVID-19 pandemic. Measurement, 167, 108288. DOI: https://doi.org/10.1016/j.measurement.2020.108288
Biamonte, J., Wittek, P., Pancotti, N., Rebentrost, P., Wiebe, N., & Lloyd, S. (2017). Quantum Machine Learning. Nature, 549(7671), 195-202. DOI: https://doi.org/10.1038/nature23474
Kan, A. (2017). Machine Learning applications in cell image analysis. Immunology and cell biology, 95(6), 525-530. DOI: https://doi.org/10.1038/icb.2017.16
LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep Learning. nature, 521(7553), 436-444. DOI: https://doi.org/10.1038/nature14539
Kubilius, J., Bracci, S., & Op de Beeck, H. P. (2016). Deep neural networks as a computational model for human shape sensitivity. PLoS computational biology, 12(4), e1004896. DOI: https://doi.org/10.1371/journal.pcbi.1004896
Python https://www.python.org/
Bauckhage, C. (2015). NumPy/SciPy Recipes for Image Processing: Creating Fractal Images. researchgate. net, Feb.
Harris, C. R., Millman, K. J., van der Walt, S. J., Gommers, R., Virtanen, P., Cournapeau, D., ... & Oliphant, T. E. (2020). Array programming with NumPy. Nature, 585(7825), 357-362. DOI: https://doi.org/10.1038/s41586-020-2649-2
Pypi https://pypi.org/project/imutils/
Pypi https://pypi.org/project/OpenCV-python/
Python https://docs.python.org/es/3.10/library/os.html
Arévalo, V., González, J., & Ambrosio, G. (2004). La Librería de Visión Artificial OpenCV. Aplicación a la Docencia e Investigación. Base Informática, 40, 61-66.
Cascade Trainer GUI https://amin-ahmadi.com/cascade-trainer-gui/
Nofallah, S., Mehta, S., Mercan, E., Knezevich, S., May, C. J., Weaver, D., ... & Shapiro, L. (2021). Machine Learning techniques for mitoses classification. Computerized Medical Imaging and Graphics, 87, 101832. DOI: https://doi.org/10.1016/j.compmedimag.2020.101832
Downloads
Published
Issue
Section
License
Copyright (c) 2021 UPSE Scientific and Technological Magazine
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
El titular de los derechos de autor de la obra, otorga derechos de uso a los lectores mediante la licencia Creative Commons Atribución-NoComercial-CompartirIgual 4.0 Internacional. Esto permite el acceso gratuito inmediato a la obra y permite a cualquier usuario leer, descargar, copiar, distribuir, imprimir, buscar o vincular a los textos completos de los artículos, rastrearlos para su indexación, pasarlos como datos al software o usarlos para cualquier otro propósito legal.
Cuando la obra es aprobada y aceptada para su publicación, los autores conservan los derechos de autor sin restricciones, cediendo únicamente los derechos de reproducción, distribución para su explotación en formato de papel, así como en cualquier otro soporte magnético, óptico y digital.
