Using Yolo for Mask Recognition

Natalya Demidchik, D. B. Tulepbergenov, Алия Жексембаевна Кинтонова, Natalya Glazyrina, И. И. Фураева, A A Senkovskaya

2022

Closed access Metadata (CSL-JSON)
DOI 10.1109/sist54437.2022.9945784
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

This project is designed to recognize face masks on an image using TensorFlow, Keras machine learning tools, YOLO-based Convolutional Neural Network family of models and a selection of 852 photos. This technology will enable the automated verification of masks on real-time video from surveillance cameras, which will contribute to the implementation of the requirements of the Ministry of Healthcare of the Republic of Kazakhstan on the compliance with the mask regime. This application is designed to monitor wearing compliance with medical mask requirements at L.N. Gumilyov Eurasian National University in Nur-Sultan.