Detail publikace

Detecting Faces With Face Masks

PŘINOSIL, J. MALÝ, O.

Originální název

Detecting Faces With Face Masks

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

This paper deals with the evaluation of several methods for face detection when the face is covered by a mask. The methods evaluated are Haar cascade and Histogram of Oriented Gradients as feature-based approaches, Multitask Cascade Convolutional Neural Network, Max Margin Object Detection and TinyFace as convolutional neural network based approaches. Various types of face masks are considered: disposal face mask, burka, balaclava, ski helmet with ski goggles, hockey helmet with protective grill, costumes, and others. The TinyFace method achieves the best accuracy result, but also requires much more computational power than other approaches. Therefore, this paper describes an experiment to see if the accuracy of some of the remaining methods can be improved by retraining their models with new image data containing faces with various face masks.

Klíčová slova

face detection, facial mask, convolutional networks, mask categories

Autoři

PŘINOSIL, J.; MALÝ, O.

Vydáno

28. 7. 2021

ISBN

978-1-6654-2933-7

Kniha

2021 44th International Conference on Telecommunications and Signal Processing (TSP)

Strany od

259

Strany do

262

Strany počet

4

URL

BibTex

@inproceedings{BUT175496,
  author="Jiří {Přinosil} and Ondřej {Malý}",
  title="Detecting Faces With Face Masks",
  booktitle="2021 44th International Conference on Telecommunications and Signal Processing (TSP)",
  year="2021",
  pages="259--262",
  doi="10.1109/TSP52935.2021.9522677",
  isbn="978-1-6654-2933-7",
  url="https://ieeexplore.ieee.org/document/9522677"
}