基于PSI-IPENet的两帧移相干涉相位恢复算法

  • 打印
  • 收藏
收藏成功


打开文本图片集

中图分类号:O436;TP391文献标识码:A doi:10.37188/CJLCD.2025-0077 CSTR:32172.14.CJLCD.2025-0077

Two-frame phase-shifting interferometry phase retrievalalgorithmbasedonPSI-IPENet

XU Shasha 1,2 , YANG Chenglin 1,2 , LI Mingxing, GE Jiuba 1,2 , WU Jingjing 1,2 YULin 1,2 , ZHU Huaxin 1,2 ,HU Lifa1.2*

(1.College ofScience,Jiangnan University,Wuxi 214l22,China; 2. Jiangsu Provincial Research Center ofLight Industry Opto-electronic Engineering and Technology, Wuxi 214122,China ; 3. Xi'an Institute ofApplied Optics, Xi'an 71Oo18, China)

Abstract: Phase-shifting interferometry is a widely used technique in precision optical metrology. However,conventional PSI methods typically require three or more phase-shifted interferograms,which limits their applicability in dynamic measurements and vibration-sensitive environments. To address this issue,this paper proposes a deep learning-based framework named PSI-IPENet. The framework adopts a Two-to-One structure,where two phase-shifted interferograms are used as dual-channel input, corresponding to a single phase map as the supervisory signal,and a dedicated dataset is constructed for training. PSI-IPENet leverages the feature extraction capability of IPENet and incorporates the physical characteristics of interferometric imaging,thereby enhancing the robustness and noise resistance of phase retrieval. Experimental results demonstrate that the proposed method maintains high-precision phase recovery performance even with a low number of input frames. Compared with the traditional four-step phase-shifting method,it shows significant advantages in terms of signal-to-noiseratio and phase error metrics.

Key words: phase-shifting interferometry;phase retrieval; deep learning; IPENet

1引言

光学移相干涉(Phase-ShiftingInterferometry,PSI法是一种高精度和高分辨率的非接触式测量方法,广泛应用于光学元件检测、精密机械加工、材料表面分析等领域[1-3]。(剩余12840字)

monitor