Phase unwrapping using deep learning in holographic tomography

被引:18
|
作者
Gontarz, Michal [1 ]
Dutta, Vibekananda [1 ]
Kujawinska, Malgorzata [1 ]
Krauze, Wojciech [1 ]
机构
[1] Warsaw Univ Technol, Inst Micromech & Photon, 8 Boboli St, PL-02525 Warsaw, Poland
基金
欧盟地平线“2020”;
关键词
IMAGE SEGMENTATION; ROBUST; NETWORK;
D O I
10.1364/OE.486984
中图分类号
O43 [光学];
学科分类号
070207 ; 0803 ;
摘要
Holographic tomography (HT) is a measurement technique that generates phase images, often containing high noise levels and irregularities. Due to the nature of phase retrieval algorithms within the HT data processing, the phase has to be unwrapped before tomographic reconstruction. Conventional algorithms lack noise robustness, reliability, speed, and possible automation. In order to address these problems, this work proposes a convolutional neural network based pipeline consisting of two steps: denoising and unwrapping. Both steps are carried out under the umbrella of a U-Net architecture; however, unwrapping is aided by introducing Attention Gates (AG) and Residual Blocks (RB) to the architecture. Through the experiments, the proposed pipeline makes possible the phase unwrapping of highly irregular, noisy, and complex experimental phase images captured in HT. This work proposes phase unwrapping carried out by segmentation with a U-Net network, that is aided by a pre-processing denoising step. It also discusses the implementation of the AGs and RBs in an ablation study. What is more, this is the first deep learning based solution that is trained solely on real images acquired with HT.
引用
收藏
页码:18964 / 18992
页数:29
相关论文
共 50 条
  • [41] Phase unwrapping by varying the reconstruction distance in digital holographic microscopy
    Khmaladze, A.
    Epstein, T.
    Chen, Z.
    OPTICS LETTERS, 2010, 35 (07) : 1040 - 1042
  • [42] A QUASI HETERODYNE HOLOGRAPHIC TECHNIQUE AND AUTOMATIC ALGORITHMS FOR PHASE UNWRAPPING
    TOWERS, DP
    JUDGE, TR
    BRYANSTONCROSS, PJ
    FRINGE PATTERN ANALYSIS, 1989, 1163 : 95 - 119
  • [43] PHASE RECONSTRUCTION AND UNWRAPPING FROM HOLOGRAPHIC INTERFEROGRAMS OF PARTIALLY ABSORBENT PHASE OBJECTS
    VANDENHOUTEN, R
    GREBE, R
    APPLIED OPTICS, 1995, 34 (08): : 1401 - 1406
  • [44] METHOD FOR CALCULATING THE DYNAMIC PHASE DELAY IN HOLOGRAPHIC INTERFEROMETRY WITHOUT PHASE UNWRAPPING
    Belashov, A. V.
    Petrov, N. V.
    Semenova, I. V.
    COMPUTER OPTICS, 2014, 38 (04) : 710 - 716
  • [45] The PHU-NET: A robust phase unwrapping method for MRI based on deep learning
    Zhou, Hongyu
    Cheng, Chuanli
    Peng, Hao
    Liang, Dong
    Liu, Xin
    Zheng, Hairong
    Zou, Chao
    MAGNETIC RESONANCE IN MEDICINE, 2021, 86 (06) : 3321 - 3333
  • [46] Deep learning-assisted wavefront correction with sparse data for holographic tomography
    Lin, Li-Chien
    Huang, Chung-Hsuan
    Chen, Yi-Fan
    Chu, Daping
    Cheng, Chau-Jern
    OPTICS AND LASERS IN ENGINEERING, 2022, 154
  • [47] Two-dimensional phase unwrapping by a high-resolution deep learning network
    Huang, Wangwang
    Mei, Xuesong
    Wang, Yage
    Fan, Zhengjie
    Chen, Cheng
    Jiang, Gedong
    MEASUREMENT, 2022, 200
  • [48] MoDL-PU: Model-Based Deep Learning for InSAR Phase Unwrapping
    Zhou, Lifan
    Yu, Hanwen
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2025, 63
  • [49] A DETAIL-PRESERVATION METHOD OF DEEP LEARNING ONE-STEP PHASE UNWRAPPING
    Ye, Xin
    Qian, Jiang
    Wang, Yong
    Yu, Hanwen
    Wang, Lu
    2022 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2022), 2022, : 1115 - 1118
  • [50] VDE-Net: a two-stage deep learning method for phase unwrapping
    Zhao, Jiaxi
    Liu, Lin
    Wang, Tianhe
    Wang, Xianzhou
    DU, Xiaohui
    Hao, Ruqian
    Liu, Juanxiu
    Liu, Yong
    Zhang, Jing
    OPTICS EXPRESS, 2022, 30 (22) : 39794 - 39815