Masked Face Analysis via Multi-Task Deep Learning

Author(s)

Vatsa S. Patel, University of DaytonFollow
Zhongliang Nie, University of DaytonFollow
Trung-Nghia Le (0000-0002-7363-2610), National Institute of InformaticsFollow
Tam Van Nguyen (0000-0003-0236-7992), University of DaytonFollow

Document Type

Article

Publication Date

10-5-2021

Publication Source

Journal of Imaging

Abstract

Face recognition with wearable items has been a challenging task in computer vision and involves the problem of identifying humans wearing a face mask. Masked face analysis via multi-task learning could effectively improve performance in many fields of face analysis. In this paper, we propose a unified framework for predicting the age, gender, and emotions of people wearing face masks. We first construct FGNET-MASK, a masked face dataset for the problem. Then, we propose a multi-task deep learning model to tackle the problem. In particular, the multi-task deep learning model takes the data as inputs and shares their weight to yield predictions of age, expression, and gender for the masked face. Through extensive experiments, the proposed framework has been found to provide a better performance than other existing methods.

ISBN/ISSN

2313-433X

Document Version

Published Version

Comments

This open-access article is provided for download in compliance with the publisher’s policy on self-archiving. To view the version of record, use the DOI: https://doi.org/10.3390/jimaging7100204

Publisher

MDPI

Volume

7

Peer Reviewed

yes

Issue

10

Sponsoring Agency

Ministry of Education, Culture, Sports, Science and Technology, Japan (MEXT) ; Japan Society for the Promotion of Science Grants-in-Aid for Scientific Research (KAKENHI)

eCommons Citation

Patel, Vatsa S.; Nie, Zhongliang; Le, Trung-Nghia; and Nguyen, Tam Van, "Masked Face Analysis via Multi-Task Deep Learning" (2021). Computer Science Faculty Publications. 195.
https://ecommons.udayton.edu/cps_fac_pub/195