Skip to main content
IOP - PMC COVID-19 Collection logoLink to IOP - PMC COVID-19 Collection
. 2020 Apr;1518(1):012041. doi: 10.1088/1742-6596/1518/1/012041

Application of a Novel and Improved VGG-19 Network in the Detection of Workers Wearing Masks

Jian Xiao 1, Jia Wang 1, Shaozhong Cao 1, Bilong Li 1
PMCID: PMC7347244  PMID: 34191934

Abstract

In order to work and travel safely during the outbreak of COVID-19, a method of security detection based on deep learning is proposed by using machine vision instead of manual monitoring. To detect the illegal behaviors of workers without masks in workplaces and densely populated areas, an improved convolutional neural network VGG-19 algorithm is proposed under the framework of tensorflow, and more than 3000 images are collected for model training and testing. Using VGG-19 network model, three FC layers are optimized into one flat layer and two FC layers with reduced parameters. The softmax classification layer of the original model is replaced by a 2-label softmax classifier. The experimental results show that the precision of the model is 97.62% and the recall is 96.31%. The precision of identifying the workers without masks is 96.82%, the recall is 94.07%, and the data set provided has a high precision. For the future social health and safety to provide favorable test data.

References

  • [1].Fan Shu Bao. Problems and countermeasures in chemical safety production [J] Chemical Engineering & Equipment. 2018;01:266–268. [Google Scholar]
  • [2].Guan Li Jun. Prevent chemical accidents and optimize chemical safety design [J] Chemical Engineering Design Communications. 2019;45(04):175–176. [Google Scholar]
  • [3].Liu G L, Gingold Y, Lien J M. Continuous visibility feature; 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2015. [Google Scholar]
  • [4].Seo J, Han S, Lee S, et al. Computer vision techniques for construction safety and health monitoring[J] Advanced Engineering Informatics. 2015;29(2) 239251. [Google Scholar]
  • [5].Traffic sign recognition using a multi-task convolutional neural network. Luo H, Yang Y, Tong B, et al. IEEE Transactions on Intelligent Transportation Systems. 2017.
  • [6].Liu Tong, Wang Zheng. HiCNN: a very deep convolutional neural network to better enhance the resolution of Hi-C data[J] Bioinformatics; Oxford, England: 2019. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • [7].Lin Zhang, Niu Yuan Fei, Rui Zhang Wen, Ling Zeng Xia. Review of Full Convolutional Neural Networks [J/OL] Computer Engineering and Applications. pp. 1–14. 2019-11-13.
  • [8].Ha Inhae, Kim Hongjo, Park Somin, Hyoungkwan Kim. Image retrieval using BIM and features from pretrained VGG network for indoor localization[J] Building and Environment. 2018;140 [Google Scholar]
  • [9].Evgeny A., Smirnov Denis M., Timoshenko Serge N., Andrianov Comparison of Regularization Methods for ImageNet Classification with Deep Convolutional Neural Networks[J] AASRI Procedia. 2014;6 [Google Scholar]
  • [10].Dashdoij Zolzaya, Min Song. An application of convolutional neural networks with salient features for relation classification[J] BMC Bioinformatics. 2019;20(10) doi: 10.1186/s12859-019-2808-3. [DOI] [PMC free article] [PubMed] [Google Scholar]

Articles from Journal of Physics. Conference Series are provided here courtesy of IOP Publishing

RESOURCES