High Power Laser and Particle Beams, Volume. 34, Issue 11, 112002(2022)
Using deep learning for surface defects identification of optical components
Figures & Tables(9)
Fig. 5. Training results with different number of convolution layers
Table 1. Comparison of classification accuracy of different methods
View tableView in ArticleTable 1. Comparison of classification accuracy of different methods
input channels classifier accuracy/% − SVM[ 2 ]92.2 1 SVM (Linear) SVM (RBF) LeNet-5 76.6 60.0 73.3 ICFNet 90.0 3 SVM (Linear) 76.6 SVM (RBF) 63.3 LeNet-5 86.7 ICFNet 96.7(+4.5)
Tools
Get Citation
Copy Citation Text
Yanhua Shao, Yupei Feng, Xiaoqiang Zhang, Hongyu Chu. Using deep learning for surface defects identification of optical components[J]. High Power Laser and Particle Beams, 2022, 34(11): 112002
Paper Information
Category: Inertial Confinement Fusion Physics and Technology
Received: Jan. 13, 2022
Accepted: Jun. 8, 2022
Published Online: Oct. 18, 2022
The Author Email: Chu Hongyu (chuhongyu@swust.edu.cn)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20