banner
Home > Open Journal Systems

Application of Artificial Intelligence in Monitoring the Use of Protective Masks

Alexandre Pereira Junior, Thiago Pedro Donadon Homem

Abstract


In the context of current epidemic diseases, this study developed a web application, which can monitor the use of protective masks in public environments. Using the Flask framework in Python language, the application has a control panel to help visualize the obtained data. In the detection process, Haar Cascade algorithm is used to classify faces with and without protective masks. Therefore, the web applications are lightweight, allowing the detection and storage of images captured in the cloud and thte possibility of further data analysis. The classifier presents precision, reversal and f-score of 63%, 93% and 75%, respectively. Although the accuracy is satisfactory, new experiments will be carried out to explore new computer vision technologies, such as the use of deep learning.


Keywords


Computer application, COVID-19, Facial detection, Haar Cascade, Artificial intelligence, Prevention

Full Text:

PDF

References


1. Vieira J, Ricardo O, Hannah C, et al. What do we know about COVID-19? Revista Da Associação Médica Brasileira 2020; 66 (4): 534–540.

2. Reis F. Esteudo avalia efeka Das mascados de prot é no coronaverus. Pfarma; 2020.

3. Hewings-Martin Y. How do SARS and MERS compare with COVID-19? Medical News Today; 2020.

4. Diário Oficial de São Paulo. Decreto 59396 2020 de São Paulo SP; 2020. Available from: https://bit.ly/3hb-hJGbb.

5. Sistema de Monitoramento Inteligente do Governo de São Paulo (SIMI-SP). Isolamento 2020. Gov-erno do Estado de São Paulo. Available from: https://www.saopaulo.sp.gov.br/coronavirus/isolamento/.

6. Pontes R. Inteligência artificial nos investimentos. Clube de Autores (managed); 2011.

7. Backes AR, Junior JJ. Introdução à visão com-putacional usando Matlab. Alta Books Editora; 2019.

8. Almanza JC, Visão computacional e aprendizagem automática para aplicações em agropecuária e ciências forenses; 2018. Available from: http://www.gpec.ucdb.br/pistori/orientacoes/planos/carlos2018.pdf.

9. Kissler SM, Tedijanto C, Goldstein E, et al. Pro-jecting the transmission dynamics of SARS-CoV-2 through the postpandemic period. Science 2020; 368(6493): 860–868.

10. Portal do Governo. Governo de SP apresenta Sistema de Monitoramento Inteligente contra coronavírus. Governo do Estado de São Paulo; 2020. Available from: https://bit.ly/2X3ReFn

11. Araujo ZL,Rrosito J C. The deep neural network is used to detect the gender in wild animals in real time. In 2018, the 31st sibrapi graphics, patterns and images Conference (sibrapi). 2018. p. 118-125. https://doi.org/10.1109/sibgrapi.2018.00022.

12. Botelho G, Papa J, Marana A. On learning the deep local features of robust face deception detection. In 2018, the 31st sibrapi graphics, patterns and images Conference (sibrapi). 2018. p. 258-265. Https://doi.org/10.1109/sibgrapi.2018.00040.

13. Finizola JS, Tagino JM, Teodoro FG, Lima CA. (2019). A comparative study of deep face, auto-encoder and traditional machine learning tech-nology for biometric face recognition. 2019 In-ternational Joint Conference on neural networks (IJCNN). 2019. p. 1–8.

14. Mordvintsev A. Face detection using Haar cascade. OpenCV-Python Tutorials 2013.

15. Viol P, Jones M. Enhanced cascading fast object detection using simple features. Proceedings of the 2001 IEEE Computer Society Conference on computer vision and pattern recognition. CVPR 2001. Https://doi.org/10.1109/CVPR.2001.990517.

16. Lienhart R, Maydt J. An extended set of Haar-like features for rapid object detection. En Proceedings. International Conference on Image Processing 2002. Available from: Https://doi.org/10.1109/ICIP.2002.1038171

17. Duarte JC. O algorithm enhancement at startup and its application. Coleção Digital 2009.

18. Harmouch M. The Haar cascade classifier in opencv intuitively explains this. Medium 2020.

19. OpenCV Team. Opencv 2020. Available from: Https://opencv.org/.

20. MongoDB Inc..Montgobu atlas 2020. Available from: Https://www.mongodb.com/cloud/atlas

21. Dirolf, M. Pimongo: Python driver for mongodb (3.11.0) [software]. Python 2020. Available from: https://pypi.org/Project/pimongo/.

22. Clark A, Lundh F, GitHub contributors. Pillow: Python Imaging Library (7.2.0) [software]. Python 2020. Available from: https://python-pillow.org.

23. Pallets (s. f.). Welcome to Flask’s documentation [página web]. Consultado el 14 de agosto de 2020. Available from: https://flask.palletsprojects.com/en/1.1.x/.

24. OpenJS Foundation. Jquery 2020. Available from: Https://jquery.com/.

25. Kunz G. Chart. Chartist.js Simple responsive charts 2019. Available from: Https://gionkunz.github.io/chartist-js/.

26. Chang A, Wang A, Mark A, et al. Documentation [software]. Google 2020. Available from: Https://materializecss.com/.

27. Gehanno JF, Rollin L, Le Jean T, et al. Determine the accuracy and recall of the search strategy of MEDLINE rework study. Journal of Occupational Rehabilitation 2009. 19 (3):223–230.

28. Magdy W, Jones GJ. Chairman: Evaluate the scoring criteria for recall oriented information re-trieval applications. Proceedings of the 33rd ACM SIGIR International Conference on research and development of information retrieval. 2010. p. 611–618.




DOI: https://doi.org/10.32629/jai.v4i2.500

Refbacks

  • There are currently no refbacks.


Copyright (c) 2021 Alexandre Pereira Junior, Thiago Pedro Donadon Homem

License URL: https://creativecommons.org/licenses/by-nc/4.0