Convolutional neural network for estimating physical parameters from Newton's rings

被引：5

作者：

Li, Peihang ^{[1
,2
]}

Lu, Ming-Feng ^{[1
,2
]}

Ji, Chen-Chen ^{[3
]}

Wu, Jin-Min ^{[4
]}

Liu, Zhe ^{[5
]}

Wang, Chenyang ^{[6
]}

Zhang, Feng ^{[1
,2
]}

Tao, Ran ^{[1
,2
]}

机构：

[1] Beijing Inst Technol, Sch Informat & Elect, Beijing 100081, Peoples R China

[2] Beijing Key Lab Fract Signals & Syst, Beijing 100081, Peoples R China

[3] Chinese Acad Sci, Inst Software, Beijing 100190, Peoples R China

[4] Beijing Informat Sci & Technol Univ, Sch Automat, Beijing 100101, Peoples R China

[5] Beijing Inst Technol, Sch Mech Engn, Beijing 100081, Peoples R China

[6] Beijing Inst Technol, Sch Phys, Beijing 100081, Peoples R China

来源：

APPLIED OPTICS | 2021年 / 60卷 / 13期

基金：

中国国家自然科学基金;

关键词：

DEEP; PROJECTION; NET;

D O I：

10.1364/AO.422012

中图分类号：

O43 [光学];

学科分类号：

070207 ; 0803 ;

摘要：

By analyzing Newton's rings, often encountered in interferometry, the parameters of spherical surfaces such as the rings' center and the curvature radius can be estimated. First, the classical convolutional neural networks, visual geometry group (VGG) network and U-Net, are applied to parameter estimation of Newton's rings. After these models are trained, the rings' center and curvature radius can be obtained simultaneously. Compared with previous analysis methods of Newton's rings, it is shown that the proposed method has higher precision, better immunity to noise, and lower time consumption. For a Newton's rings pattern of 640 x 480 pixels comprising 5 dB Gaussian noise or 60% salt-and-pepper noise, the parameters can be estimated by the VGG model in 0.01 s, the error of the rings' center is less than one pixel, and the error of curvature radius is lower than 0.5%. (C) 2021 Optical Society of America

引用

页码：3964 / 3970

页数：7

共 50 条

[31] On the convergence of Newton's method when estimating higher dimensional parameters
Clarke, Brenton R.
Futschik, Andreas
JOURNAL OF MULTIVARIATE ANALYSIS, 2007, 98 (05) : 916 - 931
[32] Random Sharing Parameters in the Global Region of Convolutional Neural Network
Dai D.
Zhuang Z.
Wei J.
Xia S.
Li Y.
Zhu H.
IEEE Transactions on Artificial Intelligence, 2022, 3 (05): : 738 - 748
[33] Oceanic turbulence parameters recognition based on convolutional neural network
Gao, Siyu
Liu, Xiaoyun
Chen, Yonghao
Jiang, Jinyang
Liu, Ying
Chai, Tengfei
Jiang, Yueqiu
JOURNAL OF OPTICS, 2024, 26 (07)
[34] Linear Blur Parameters Estimation Using a Convolutional Neural Network
Nasonov, A., V
Nasonova, A. A.
PATTERN RECOGNITION AND IMAGE ANALYSIS, 2022, 32 (03) : 611 - 615
[35] Physical Security Assessment with Convolutional Neural Network Transfer Learning
Stubbs, Jaclynn J.
Birch, Gabriel C.
Woo, Bryana L.
Kouhestani, Camron G.
2017 INTERNATIONAL CARNAHAN CONFERENCE ON SECURITY TECHNOLOGY (ICCST), 2017,
[36] The Impact of Convolutional Neural Network Parameters in the Binary Classification of Mammograms
Dicu, Madalina
Diosan, Laura
Andreica, Anca
Chira, Camelia
Cordos, Alin
2022 24TH INTERNATIONAL SYMPOSIUM ON SYMBOLIC AND NUMERIC ALGORITHMS FOR SCIENTIFIC COMPUTING, SYNASC, 2022, : 181 - 188
[37] Impact of Convolutional Neural Network Input Parameters on Classification Performance
Maitra, Sanjit
Ojha, Rahul Kumar
Ghosh, Kuntal
2018 4TH INTERNATIONAL CONFERENCE FOR CONVERGENCE IN TECHNOLOGY (I2CT), 2018,
[38] Linear Blur Parameters Estimation Using a Convolutional Neural Network
A. V. Nasonov
A. A. Nasonova
Pattern Recognition and Image Analysis, 2022, 32 : 611 - 615
[39] Deep convolutional neural networks for estimating porous material parameters with ultrasound tomography
1600, Acoustical Society of America (143):
[40] Deep convolutional neural networks for estimating porous material parameters with ultrasound tomography
Lahivaara, Timo
Karkkainen, Leo
Huttunen, Janne M. J.
Hesthaven, Jan S.
JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 2018, 143 (02): : 1148 - 1158

← 1 2 3 4 5 →