CCTV based system for detection of anti-virus masks

This paper presents the use of neural networks to detect people with anti-virus masks. The algorithm allows to determine if a person has a correctly worn mask (covered nose and mouth). The use of neural networks has been compared with typical Haar cascade frontal face solutions available in the Open...

Full description

Saved in:
Bibliographic Details
Main Authors: Podbucki, Kacper, Suder, Jakub, Marciniak, Tomasz, Dabrowski, Adam
Format: Conference Proceeding
Language:English
Subjects:
anti-virus masks
convolutional neural networks
COVID-19
Face detection
Face recognition
Faces
Image resolution
mask detection
Neural networks
OpenCV
Python programming
Software
vision system
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper presents the use of neural networks to detect people with anti-virus masks. The algorithm allows to determine if a person has a correctly worn mask (covered nose and mouth). The use of neural networks has been compared with typical Haar cascade frontal face solutions available in the OpenCV library. The proposed solution has been checked for efficiency and precision, as well as for the minimum resolution requirements of the resulting facial image. The software works on still images as well as on video sequences from computer webcams and CCTV cameras.
ISSN:2326-0262
2326-0319
DOI:10.23919/SPA50552.2020.9241303