Mask Wearing Specification Detection System Based on Residual Network

DOI

10.2991/978-94-6463-242-2_68How to use a DOI?

Keywords

Residual network; mask detection; fitting error

Abstract

In order to solve the problem of normative detection of mask wearing, this paper proposes an LMSE-ResNet based on improved residual network. Firstly, the cascade classifier is used to strengthen the features of the mask-wearing part, detect whether the face in the image wears a mask, and then load the pre-trained weights and parameters into the convolutional layer of the new model. The number of channels of feature mapping is increased while reducing the residual network depth, and finally the fitting error of the minimum mean square linear model is used as the loss function to improve the detection accuracy. In the experiment on the public dataset Masked Face-Net, the algorithm achieves higher accuracy and lower loss value, and has better effect and robustness in detecting mask wearing irregularities.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - YuChen Zhang
AU  - ZiQi Shao
AU  - YaNan Chen
AU  - GuangHan Guo
AU  - HangXu Wu
PY  - 2023
DA  - 2023/09/22
TI  - Mask Wearing Specification Detection System Based on Residual Network
BT  - Proceedings of the 2023 4th International Conference on Artificial Intelligence and Education (ICAIE 2023)
PB  - Atlantis Press
SP  - 554
EP  - 562
SN  - 2589-4900
UR  - https://doi.org/10.2991/978-94-6463-242-2_68
DO  - 10.2991/978-94-6463-242-2_68
ID  - Zhang2023
ER  -