Two-step Data Augmentation for Masked Face Detection and Recognition: Turning Fake Masks to Real

Yan Aaren, George Bebis, Mircea Nicolescu

2022

Abstract

The COVID-19 spread raised urgent requirements for masked face recognition and detection tasks. However, the current masked face datasets are insufficient. To alleviate the limitation of data, we proposed a two-step data augmentation that combines rule-based mask warping with unpaired image-to-image translation. Our qualitative evaluations showed that our method achieved noticeable improvements compared to the rule-based warping alone and complemented results from other state-of-the-art GAN-based generation methods, such as IAMGAN. The non-mask change loss and the noise input we used to improve training showed effectiveness. We also provided an analysis of potential future directions based on observations of our experiments.

Paper Citation

in Harvard Style

Aaren Y., Bebis G. and Nicolescu M. (2022). Two-step Data Augmentation for Masked Face Detection and Recognition: Turning Fake Masks to Real. In Proceedings of the 2nd International Conference on Image Processing and Vision Engineering - Volume 1: IMPROVE, ISBN 978-989-758-563-0, pages 126-134. DOI: 10.5220/0011037900003209

in Bibtex Style

@conference{improve22,
author={Yan Aaren and George Bebis and Mircea Nicolescu},
title={Two-step Data Augmentation for Masked Face Detection and Recognition: Turning Fake Masks to Real},
booktitle={Proceedings of the 2nd International Conference on Image Processing and Vision Engineering - Volume 1: IMPROVE,},
year={2022},
pages={126-134},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011037900003209},
isbn={978-989-758-563-0},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 2nd International Conference on Image Processing and Vision Engineering - Volume 1: IMPROVE,
TI - Two-step Data Augmentation for Masked Face Detection and Recognition: Turning Fake Masks to Real
SN - 978-989-758-563-0
AU - Aaren Y.
AU - Bebis G.
AU - Nicolescu M.
PY - 2022
SP - 126
EP - 134
DO - 10.5220/0011037900003209