Resumen

CHUQUIMARCA JIMENEZ, Luis; PINZON TITUANA, Santiago  y  ROSALES PINCAY, Anthony. Mask detection for COVID-19 through of Deep Learning using OpenCV and Cascade Trainer GUI. RCTU [online]. 2021, vol.8, n.1, pp.68-73. ISSN 1390-7697.  https://doi.org/10.26423/rctu.v8i1.572.

The pandemic of covid-19 is causing a health crisis worldwide, one of the recommendations of scientists and governments to avoid contagion is the use of masks. Based on this, this paper shows the development of a software to detect the mask in different scenarios using Python programming language through cv2, os, Numpy and Imutils libraries, using convolutional neural networks more efficient than common neural networks, which were trained with Cascade Trainer GUI software, using different data-base quantities from 400 to 1400 images to compare the different types of accuracy of the mask detection system. However, the first database did not have a good pressure due to a low number of false positives, so as more data was used, the accuracy increased considerably until an accuracy of 92% with mask and 100% without mask was obtained.

Palabras clave : Machine Learning; Deep Learning; convolutional networks; false positives..

        · resumen en Español     · texto en Español     · Español ( pdf )