Speckle noise reduction in coherent imaging based on deep learning without clean data

Abstract In this paper, we propose a new algorithm based on deep learning to reduce the speckle noise for coherent imaging without clean data. By learning the common information, namely the clean image, from paired noisy holographic reconstructed images, the noise reduction mechanism of the system can be obtained. Unlike normal deep learning methods, our algorithm does not require prior knowledge of clean object distribution. Experimental results show that noise removal effect of proposed method is better than traditional smoothing algorithms and can be comparable to the existed deep learning method trained with clean data.

[1]  Chau-Jern Cheng,et al.  Digital hologram for data augmentation in learning-based pattern classification. , 2018, Optics letters.

[2]  Bahram Javidi,et al.  Quasi noise-free digital holography , 2016, Light: Science & Applications.

[3]  Yibo Zhang,et al.  Phase recovery and holographic image reconstruction using deep learning in neural networks , 2017, Light: Science & Applications.

[4]  Cheng-Huan Chen,et al.  Low speckle laser illuminated projection system with a vibrating diffractive beam shaper , 2012 .

[5]  Lei Tian,et al.  Deep speckle correlation: a deep learning approach toward scalable imaging through scattering media , 2018, Optica.

[6]  Joseph W Goodman,et al.  Versatile method for achieving 1% speckle contrast in large-venue laser projection displays using a stationary multimode optical fiber. , 2012, Optics express.

[7]  Qiong-Hua Wang,et al.  Speckle noise suppression method in holographic display using time multiplexing , 2017 .

[8]  R. Gerchberg.  A practical algorithm for the determination of phase from image and diffraction plane pictures , 1972 .

[9]  Guang-Can Guo,et al.  Deep hybrid scattering image learning , 2018, Journal of Physics D: Applied Physics.

[10]  Van Lam,et al.  Automatic phase aberration compensation for digital holographic microscopy based on deep learning background detection. , 2017, Optics express.

[11]  Shy Shoham,et al.  Speckle elimination using shift-averaging in high-rate holographic projection. , 2009, Optics express.

[12]  Osamu Matoba,et al.  Image reconstruction algorithm for recovering high-frequency information in parallel phase-shifting digital holography [Invited]. , 2013, Applied optics.

[13]  Edward Buckley,et al.  Holographic Laser Projection , 2011, Journal of Display Technology.

[14]  Tomer Michaeli,et al.  Deep-STORM: super-resolution single-molecule microscopy by deep learning , 2018, 1801.09631.

[15]  B Javidi,et al.  Random resampling masks: a non-Bayesian one-shot strategy for noise reduction in digital holography. , 2013, Optics letters.

[16]  Yasuhiro Takaki,et al.  Speckle-free and grayscale hologram reconstruction using time-multiplexing technique. , 2011, Optics express.

[17]  Bahram Javidi,et al.  Reduction of speckle in digital holography by discrete Fourier filtering. , 2007, Journal of the Optical Society of America. A, Optics, image science, and vision.

[18]  Lei Tian,et al.  Deep learning approach for Fourier ptychography microscopy. , 2018, Optics express.

[19]  Wonseok Jeon,et al.  Speckle noise reduction for digital holographic images using multi-scale convolutional neural networks. , 2018, Optics letters.

[20]  Guohai Situ,et al.  Learning-based lensless imaging through optically thick scattering media , 2019, Advanced Photonics.

[21]  Jui-Wen Pan,et al.  Speckle reduction and maintaining contrast in a LASER pico-projector using a vibrating symmetric diffuser. , 2014, Optics express.

[22]  Daniel Velásquez Prieto,et al.  Reduction of speckle noise in digital holography by using digital image processing , 2005 .

[23]  Jorge Garcia-Sucerquia,et al.  Speckle noise reduction in digital holography by slightly rotating the object , 2016 .

[24]  Guohai Situ,et al.  eHoloNet: a learning-based end-to-end approach for in-line digital holographic reconstruction. , 2018, Optics express.

[25]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.

[26]  Gunho Choi,et al.  Cycle-consistent deep learning approach to coherent noise reduction in optical diffraction tomography. , 2018, Optics express.

[27]  Yibo Zhang,et al.  Deep Learning Microscopy , 2017, ArXiv.

[28]  Jun Tanida,et al.  Deep learning wavefront sensing. , 2019, Optics express.

[29]  Mitsuo Takeda,et al.  Laser speckle reduction by multimode optical fiber bundle with combined temporal, spatial, and angular diversity. , 2012, Applied optics.

[30]  Michal Makowski,et al.  Minimized speckle noise in lens-less holographic projection by pixel separation. , 2013, Optics express.