
Fast phase retrieval in off-axis digital holographic microscopy through deep learning
Author(s) -
Gong Zhang,
Tian Guan,
Zhiyuan Shen,
Xiangnan Wang,
Tao Hu,
Delai Wang,
Yonghong He,
Na Xie
Publication year - 2018
Publication title -
optics express
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.394
H-Index - 271
ISSN - 1094-4087
DOI - 10.1364/oe.26.019388
Subject(s) - digital holography , digital holographic microscopy , holography , computer science , phase retrieval , convolutional neural network , optics , artificial intelligence , phase (matter) , focus (optics) , compensation (psychology) , computer vision , digital imaging , microscope , microscopy , digital image processing , image processing , deep learning , artificial neural network , digital image , image (mathematics) , fourier transform , physics , psychology , quantum mechanics , psychoanalysis
Traditional digital holographic imaging algorithms need multiple iterations to obtain focused reconstructed image, which is time-consuming. In terms of phase retrieval, there is also the problem of phase compensation in addition to focusing task. Here, a new method is proposed for fast digital focus, where we use U-type convolutional neural network (U-net) to recover the original phase of microscopic samples. Generated data sets are used to simulate different degrees of defocused image, and verify that the U-net can restore the original phase to a great extent and realize phase compensation at the same time. We apply this method in the construction of real-time off-axis digital holographic microscope and obtain great breakthroughs in imaging speed.