High-precision deep learning-based single-frame interferometric decoupling for measuring optical homogeneity of parallel plates

ZHOU Shunye; TANG Liang; CUI Han; QIU Lirong; ZHAO Weiqian

doi:null

您当前的位置：

首页 >

文章列表页 >

High-precision deep learning-based single-frame interferometric decoupling for measuring optical homogeneity of parallel plates

更新时间：2026-06-26

- High-precision deep learning-based single-frame interferometric decoupling for measuring optical homogeneity of parallel plates
- Optics and Precision Engineering Pages: 1-12(2026)
- 作者机构：
  
  北京理工大学光电学院，北京 100081
- 作者简介：
- 基金信息：
- DOI：
  CLC： TH741;TP183
- Received：14 April 2026，
  
  Revised：2026-04-17，
  
  Online First：26 June 2026，
- 稿件说明：
移动端阅览
周顺业,汤亮,崔晗等.基于深度学习单帧干涉解耦的平行平板光学均匀性高精度测量[J].光学精密工程,

ZHOU Shunye,TANG Liang,CUI Han,et al.High-precision deep learning-based single-frame interferometric decoupling for measuring optical homogeneity of parallel plates[J].Optics and Precision Engineering,
周顺业,汤亮,崔晗等.基于深度学习单帧干涉解耦的平行平板光学均匀性高精度测量[J].光学精密工程, DOI：10.37188/OPE.XXXXXXXX.0001 CSTR：32169.14.OPE.XXXXXXXX.0001

ZHOU Shunye,TANG Liang,CUI Han,et al.High-precision deep learning-based single-frame interferometric decoupling for measuring optical homogeneity of parallel plates[J].Optics and Precision Engineering, DOI：10.37188/OPE.XXXXXXXX.0001 CSTR：32169.14.OPE.XXXXXXXX.0001

摘要

平行平板作为典型透射光学元件，广泛应用于光学检测、半导体制造及国防装备等领域，其光学均匀性对系统性能具有重要影响。针对现有光学均匀性高精度测量中存在的干涉混叠难以解耦、多帧采集耗时较长及环境噪声抑制困难等问题，提出一种基于深度学习单帧干涉解耦的平行平板光学均匀性高精度测量方法。首先，通过构建混叠干涉图与单面干涉图之间的映射模型对单帧混叠干涉图进行解耦，从而获得前后表面各自的单表面干涉图，以实现干涉条纹有效分离。然后，通过虚拟移相重构由单帧干涉图生成的等移相间隔序列，结合传统五步移相法进行相位提取与面形重建，进而实现平行平板光学均匀性高精度检测。本文构建了两阶段卷积神经网络模型，第一阶段网络用于实现混叠条纹到单面条纹的映射，第二阶段网络完成五步移相序列生成及前后表面面形解算，搭建了基于深度学习单帧干涉解耦的平行平板光学均匀性测量装置，并采用

75 mm和

50 mm平行平板样品进行了实验验证。实验结果表明，该方法测得的光学均匀性结果与ZYGO干涉仪测量结果一致性较好，绝对偏差达到10

-7

量级。仅需采集单帧混叠干涉图即可实现平行平板光学均匀性的高精度、快速测量，可为光学元件的高通量和现场化检测提供技术支撑。

Abstract

As typical transmission optical components， parallel plates are widely used in optical detection， semiconductor manufacturing and defense equipment， etc. Their optical homogeneity has a significant impact on system performance. In response to the problems such as the difficulty in decoupling interference aliasing， the long time consumption of multi-frame acquisition， and the difficulty in suppressing environmental noise in the existing high-precision measurement of optical homogeneity， this paper proposes a high-precision deep learning-based single-frame interferometric decoupling method for measuring optical homogeneity of parallel plates. This method first decouples the single-frame aliased interferogram through constructing a mapping model between the aliased interferogram and the single-sided interferogram， obtaining the single-sided interferograms of front and back surfaces， and achieving effective separation of interference fringes. Then， by virtual phase-shifting reconstruction， an equal phase shift interval sequence is generated from the single-frame interferogram. Combined with the traditional five-step phase-shifting method for phase extraction and surface profile reconstruction， it ac

hieves high-precision detection of optical homogeneity of parallel plates. This paper constructed a two-stage convolutional neural network model. The first-stage network is used to realize the mapping from aliased fringes to single-sided fringes. The second-stage network realizes the generation of the five-step phase-shifting sequence and the solution of surface profile of front and back surfaces. A deep learning-based single-frame interferometric decoupling experimental device for measuring optical homogeneity of parallel plates was developed. Experiments were conducted using Φ75 mm and Φ50 mm parallel plate samples. The results indicate that the detection results of optical homogeneity obtained by the proposed method are in good agreement with those measured by ZYGO interferometer. The absolute deviations are on the order of 10

-7

. This approach requires only single-frame aliased interferogram to achieve the high-precision and rapid measurement of optical homogeneity， which provides technical support for high-throughput and on-site inspection of optical components.

关键词

Keywords

references

李强，刘昂，高波，等 . 光学材料光学不均匀性绝对测量误差分析［J］. 应用光学， 2013 ， 34 （ 3 ）： 463 - 468 .

LI Q ， LIU A ， GAO B ， et al . Error analysis of absolute test method of inhomogeneity of optical materials ［J］. Journal of Applied Optics ， 2013 ， 34 （ 3 ）： 463 - 468 . （in Chinese）

郭培基，余景池，丁泽钊，等 . 光学玻璃光学均匀性的绝对测量技术［J］. 激光杂志， 2003 ， 24 （ 3 ）： 26 - 27 .

GUO P J ， YU J CH ， DING Z ZH ， et al . Absolute testing method of the homogeneity of optical glass ［J］. Laser Journal ， 2003 ， 24 （ 3 ）： 26 - 27 . （in Chinese）

廖之山 . 基于非均匀傅里叶变换的平行平板光学均匀性的干涉测量技术研究［D］. 南京：南京理工大学， 2019 .

LIAO ZH SH . Research on Optical Homogeneity Interferometry of Parallel Plates Based on Nonuniform Fast Fourier Transform ［D］. Nanjing ： Nanjing University of Science and Technology ， 2019 . （in Chinese）

郭仁慧 . 近红外大口径波长移相干涉仪关键技术及应用研究［D］. 南京：南京理工大学， 2013 .

GUO R H . Research on Key Techniques and Applications of the Near - Infrared Large Aperture Wavelength - Tuning Interferometer ［D］. Nanjing ： Nanjing University of Science and Technology ， 2013 . （in Chinese）

周永昊，常林，何婷婷，等 . 超精密平面光学元件检测技术［J］. 自然杂志， 2023 ， 45 （ 3 ）： 157 - 176 . doi: 10.3969/j.issn.0253-9608.2023.03.002 http://dx.doi.org/10.3969/j.issn.0253-9608.2023.03.002

ZHOU Y H ， CHANG L ， HE T T ， et al . Research on measurement technology of ultra-precision planar optics ［J］. Chinese Journal of Nature ， 2023 ， 45 （ 3 ）： 157 - 176 . （in Chinese） . doi: 10.3969/j.issn.0253-9608.2023.03.002 http://dx.doi.org/10.3969/j.issn.0253-9608.2023.03.002

钱宇，郭仁慧，蒋金威，等 . 平行平板光学参数的快速高精度测量方法［J］. 光学学报， 2024 ， 44 （ 3 ）： 0312002 .

QIAN Y ， GUO R H ， JIANG J W ， et al . Fast and high-precision measurement method of optical parameters of parallel flat plates ［J］. Acta Optica Sinica ， 2024 ， 44 （ 3 ）： 0312002 . （in Chinese）

刘旭，任寰，于德强，等 . 干涉法测量光学材料光学非均匀性［J］. 激光技术， 2011 ， 35 （ 2 ）： 189 - 192 . doi: 10.3969/j.issn.1001-3806.2011.02.013 http://dx.doi.org/10.3969/j.issn.1001-3806.2011.02.013

LIU X ， REN H ， YU D Q ， et al . Measurement method for inhomogeneity of optical material by means of interferometry ［J］. Laser Technology ， 2011 ， 35 （ 2 ）： 189 - 192 . （in Chinese） . doi: 10.3969/j.issn.1001-3806.2011.02.013 http://dx.doi.org/10.3969/j.issn.1001-3806.2011.02.013

AI C ， WYANT J C . Measurement of the inhomogeneity of a window ［J］. Optical Engineering ， 1991 ， 30 （ 9 ）： 1399 - 1404 . doi: 10.1117/12.55928 http://dx.doi.org/10.1117/12.55928

李建欣，郭仁慧，朱日宏，等 . 光学材料光学均匀性的波长调谐两步绝对测量法［J］. 光学学报， 2012 ， 32 （ 11 ）： 1112007 . doi: 10.3788/aos201232.1112007 http://dx.doi.org/10.3788/aos201232.1112007

LI J X ， GUO R H ， ZHU R H ， et al . Two-step wavelength tuning absolute testing method of the optical homogeneity of optical material ［J］. Acta Optica Sinica ， 2012 ， 32 （ 11 ）： 1112007 . （in Chinese） . doi: 10.3788/aos201232.1112007 http://dx.doi.org/10.3788/aos201232.1112007

张瑞，陈磊，朱文华，等 . 点源异位同步移相法检测平行平晶的光学均匀性［J］. 光子学报， 2018 ， 47 （ 1 ）： 0112002 . doi: 10.3788/gzxb20184701.0112002 http://dx.doi.org/10.3788/gzxb20184701.0112002

ZHANG R ， CHEN L ， ZHU W H ， et al . Measuring optical homogeneity of parallel plates based on simultaneous phase-shifting by lateral displacement of point sources ［J］. Acta Photonica Sinica ， 2018 ， 47 （ 1 ）： 0112002 . （in Chinese） . doi: 10.3788/gzxb20184701.0112002 http://dx.doi.org/10.3788/gzxb20184701.0112002

LIU H Y ， YAN N ， SHAO B F ， et al . Deep learning in fringe projection： a review ［J］. Neurocomputing ， 2024 ， 581 ： 127493 . doi: 10.1016/j.neucom.2024.127493 http://dx.doi.org/10.1016/j.neucom.2024.127493

FENG S J ， CHEN Q ， GU G H ， et al . Fringe pattern analysis using deep learning ［J］. Advanced Photonics ， 2019 ， 1 （ 2 ）： 025001 . doi: 10.1117/1.ap.1.2.025001 http://dx.doi.org/10.1117/1.ap.1.2.025001

YIN W ， CHE Y X ， LI X S ， et al . Physics-informed deep learning for fringe pattern analysis ［J］. Opto-Electronic Advances ， 2024 ， 7 （ 1 ）： 230034 . doi: 10.29026/oea.2024.230034 http://dx.doi.org/10.29026/oea.2024.230034

FENG S J ， ZUO C ， ZHANG L ， et al . Generalized framework for non-sinusoidal fringe analysis using deep learning ［J］. Photonics Research ， 2021 ， 9 （ 6 ）： 1084 . doi: 10.1364/prj.420944 http://dx.doi.org/10.1364/prj.420944

GURROLA-RAMOS J ， DALMAU O ， ALARCÓN T . U-Net based neural network for fringe pattern denoising ［J］. Optics and Lasers in Engineering ， 2022 ， 149 ： 106829 . doi: 10.1016/j.optlaseng.2021.106829 http://dx.doi.org/10.1016/j.optlaseng.2021.106829

GURROLA-RAMOS J ， DALMAU O ， ALARCÓN T E . A residual dense U-Net neural network for image denoising ［J］. IEEE Access ， 2021 ， 9 ： 31742 - 31754 . doi: 10.1109/access.2021.3061062 http://dx.doi.org/10.1109/access.2021.3061062

QIAO G ， HUANG Y Y ， SONG Y P ， et al . A single-shot phase retrieval method for phase measuring deflectometry based on deep learning ［J］. Optics Communications ， 2020 ， 476 ： 126303 . doi: 10.1016/j.optcom.2020.126303 http://dx.doi.org/10.1016/j.optcom.2020.126303

WANG K Q ， LI Y ， QIAN K M ， et al . One-step robust deep learning phase unwrapping ［J］. Optics Express ， 2019 ， 27 （ 10 ）： 15100 . doi: 10.1364/oe.27.015100 http://dx.doi.org/10.1364/oe.27.015100

WANG K Q ， SONG L ， WANG C T ， et al . On the use of deep learning for phase recovery ［J］. Light： Science & Applications ， 2024 ， 13 ： 4 . doi: 10.1038/s41377-023-01340-x http://dx.doi.org/10.1038/s41377-023-01340-x

TANG L ， HAN M Z ， YANG S ， et al . High-precision large-aperture single-frame interferometric surface profile measurement method based on deep learning ［J］. International Journal of Extreme Manufacturing ， 2025 ， 7 （ 5 ）： 055601 . doi: 10.1088/2631-7990/add197 http://dx.doi.org/10.1088/2631-7990/add197

WANG F Z ， WANG C X ， GUAN Q Z . Single-shot fringe projection profilometry based on deep learning and computer graphics ［J］. Optics Express ， 2021 ， 29 （ 6 ）： 8024 . doi: 10.1364/oe.418430 http://dx.doi.org/10.1364/oe.418430

NGUYEN H ， WANG Y Z ， WANG Z Y . Single-shot 3D shape reconstruction using structured light and deep convolutional neural networks ［J］. Sensors ， 2020 ， 20 （ 13 ）： 3718 . doi: 10.3390/s20133718 http://dx.doi.org/10.3390/s20133718

YU H T ， ZHENG D L ， FU J A ， et al . Deep learning-based fringe modulation-enhancing method for accurate fringe projection profilometry ［J］. Optics Express ， 2020 ， 28 （ 15 ）： 21692 . doi: 10.1364/oe.398492 http://dx.doi.org/10.1364/oe.398492

FU Y J ， HUANG Y L ， XIAO W ， et al . Deep learning-based binocular composite color fringe projection profilometry for fast 3D measurements ［J］. Optics and Lasers in Engineering ， 2024 ， 172 ： 107866 . doi: 10.1016/j.optlaseng.2023.107866 http://dx.doi.org/10.1016/j.optlaseng.2023.107866

WANG F ， BIAN Y M ， WANG H C ， et al . Phase imaging with an untrained neural network ［J］. Light： Science & Applications ， 2020 ， 9 ： 77 . doi: 10.1038/s41377-020-0302-3 http://dx.doi.org/10.1038/s41377-020-0302-3

ZUO C ， QIAN J M ， FENG S J ， et al . Deep learning in optical metrology： a review ［J］. Light： Science & Applications ， 2022 ， 11 ： 39 . doi: 10.1038/s41377-022-00714-x http://dx.doi.org/10.1038/s41377-022-00714-x

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Multi-scale image enhancement in turbid water via spatial-frequency domain fusion

Inverse design of efficient achromatic metalens based on channel attention enhanced network

Real-time prediction of subsequent frames in broadband video based on optical flow method

Monocular vision-based spatial registration for implant surgery robots

Inpainting of large-area damaged images based on structural priors and multi-scale residual aggregation

Related Author

ZHANG Hao

ZHANG Qingwen

LIU Fei

SONG Yujia

LI Changqing

RONG Shihan

WANG Qi'an

CAI Yunxiao

Related Institution

School of Information Management， Qingdao University of Technology

School of Physics and Optoelectronic Engineering， Xidian University

School of Physical and Optoelectronic Engineering， Hangzhou Institute for Advanced Study， University of Chinese Academy of Sciences

Key Laboratory of Space Active Opto-Electronics Technology， Shanghai Institute of Technical Physics， Chinese Academy of Sciences

University of Chinese Academy of Sciences

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰