Abstract

We present a review of deep learning algorithms dedicated to the processing of speckle noise in coherent imaging. We focus on methods that specifically process de-noising of input images. Four main classes of applications are described in this review: optical coherence tomography, synthetic aperture radar imaging, digital holography amplitude imaging, and fringe pattern analysis. We then present deep learning approaches recently developed in our group that rely on the retraining of residual convolutional neural network structures to process decorrelation phase noise. The paper ends with the presentation of a new approach that uses an iterative scheme controlled by an input SNR estimator associated with a phase-shifting procedure.

© 2022 Optica Publishing Group

Deep learning for digital holography: a review

Tianjiao Zeng, Yanmin Zhu, and Edmund Y. Lam
Opt. Express 29(24) 40572-40593 (2021)

Hybrid-structure network and network comparative study for deep-learning-based speckle-modulating optical coherence tomography

Guangming Ni, Renxiong Wu, Junming Zhong, Ying Chen, Ling Wan, Yao Xie, Jie Mei, and Yong Liu
Opt. Express 30(11) 18919-18938 (2022)

Speckle denoising based on deep learning via a conditional generative adversarial network in digital holographic interferometry

Qiang Fang, Haiting Xia, Qinghe Song, Meijuan Zhang, Rongxin Guo, Silvio Montresor, and Pascal Picart
Opt. Express 30(12) 20666-20683 (2022)

Hologram classification of occluded and deformable objects with speckle noise contamination by deep learning

H. H. S. Lam, P. W. M. Tsang, and T.-C. Poon
J. Opt. Soc. Am. A 39(3) 411-417 (2022)

At the intersection of optics and deep learning: statistical inference, computing, and inverse design

Deniz Mengu, Md Sadman Sakib Rahman, Yi Luo, Jingxi Li, Onur Kulce, and Aydogan Ozcan
Adv. Opt. Photon. 14(2) 209-290 (2022)