Hybrid Transfer Learning and Broad Learning System for Wearing Mask Detection in the COVID-19 Era

Bingshu Wang; Yong Zhao; C L Philip Chen

doi:10.1109/TIM.2021.3069844

Hybrid Transfer Learning and Broad Learning System for Wearing Mask Detection in the COVID-19 Era

IEEE Trans Instrum Meas. 2021 Mar 30:70:5009612. doi: 10.1109/TIM.2021.3069844. eCollection 2021.

Authors

Bingshu Wang¹, Yong Zhao², C L Philip Chen^{3

4}

Affiliations

¹ School of SoftwareNorthwestern Polytechnical University Suzhou 215400 China.
² Key Laboratory of Integrated Microsystems, School of Electronic and Computer EngineeringPeking University Shenzhen Graduate School Shenzhen 518055 China.
³ School of Computer Science and EngineeringSouth China University of Technology Guangzhou 510641 China.
⁴ Faculty of Science and TechnologyUniversity of Macau Macau China.

Abstract

In the era of Corona Virus Disease 2019 (COVID-19), wearing a mask can effectively protect people from infection risk and largely decrease the spread in public places, such as hospitals and airports. This brings a demand for the monitoring instruments that are required to detect people who are wearing masks. However, this is not the objective of existing face detection algorithms. In this article, we propose a two-stage approach to detect wearing masks using hybrid machine learning techniques. The first stage is designed to detect candidate wearing mask regions as many as possible, which is based on the transfer model of Faster_RCNN and InceptionV2 structure, while the second stage is designed to verify the real facial masks using a broad learning system. It is implemented by training a two-class model. Moreover, this article proposes a data set for wearing mask detection (WMD) that includes 7804 realistic images. The data set has 26403 wearing masks and covers multiple scenes, which is available at "https://github.com/BingshuCV/WMD." Experiments conducted on the data set demonstrate that the proposed approach achieves an overall accuracy of 97.32% for simple scene and an overall accuracy of 91.13% for the complex scene, outperforming the compared methods.

Keywords: Broad learning system (BLS); Corona Virus Disease 2019 (COVID-19); transfer learning; wearing mask detection (WMD).

Grants and funding

This work was supported in part by the Fundamental Research Funds for the Central Universities under Grant G2020KY05113; in part by the National Key Research and Development Program of China under Grant 2019YFA0706200 and Grant 2019YFB1703600; in part by the National Natural Science Foundation of China under Grant 61702195, Grant 61751202, Grant U1813203, Grant U1801262, and Grant 61751205; in part by the Science and Technology Major Project of Guangzhou under Grant 202007030006; in part by The Science and Technology Development Fund, Macau SAR, under Grant 079/2017/A2 and Grant 0119/2018/A3; and in part by the Multiyear Research Grants of University of Macau.