Naslov
Face mask classification using MLP Classifier

Autori
Tin Ladić, Ante Mandekić

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), ostalo

Izvornik
Ri-STEM-2021 PRoceedings / Lorencin, Ivan ; Baressi Šegota, Sandi ; Car, Zlatan - Rijeka, 2021, 77-80

ISBN
978-953-8246-22-7

Skup
International Student Scientific Conference (Ri-STEM 2021)

Mjesto i datum
Rijeka, Hrvatska, 10.06.2021. - 11.06.2021

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Artificial intelligence, Face mask, Machine Learning, Multi-Layer Perceptron

Sažetak
In the trying times of the Covid-19 pandemic a need was identified to regulate the usage of masks in public places. This can be done by detecting if a person is wearing a mask or not using a camera and a detection algorithm, the camera could be placed for example at the entrance to a venue or a building. The goal of this work is to create a detection algorithm using an MLP Classifier and achieve satisfactory accuracy. Image data preparation was done using Open Computer Vision library in python, and the detection and metrics of the results were done using the Scikit-learn python library. The bestachieved accuracy was 83.85%, and it was concluded that maybe the MLP Classifier was not the best method for detecting image data.

Izvorni jezik
Engleski

Znanstvena područja
Elektrotehnika, Računarstvo, Temeljne tehničke znanosti

POVEZANOST RADA