Fringe pattern denoising based on deep learning

Abstract In this paper, deep learning as a novel algorithm is proposed to reduce the noise of the fringe patterns. Usually, the training samples are acquired through experimental acquisition, but these data can be easily obtained by simulations in the proposed algorithm. Thus, the time cost used for the whole training process is greatly reduced. The performance of the proposed algorithm has been demonstrated through the analysis on the simulated and real fringe patterns. It is obvious that the proposed algorithm has a faster calculation speed compared with existing denoising algorithm, and recovers the fringe patterns with high quality. Most importantly, the proposed algorithm may provide a solution to other denoising problems in the field of optics, such as hologram and speckle denoising.

[1]  Mamoru Mitsuishi,et al.  Simultaneous measurement of surface shape and absolute optical thickness of a glass plate by wavelength tuning phase-shifting interferometry , 2012 .

[2]  Caiming Zhang,et al.  Fringe pattern denoising via image decomposition. , 2012, Optics letters.

[3]  Manuel Servin,et al.  A parametric method applied to phase recovery from a fringe pattern based on a genetic algorithm , 2002 .

[4]  Qian Kemao,et al.  Two-dimensional windowed Fourier transform for fringe pattern analysis: Principles, applications and implementations , 2007 .

[5]  Qian Kemao,et al.  Windowed Fourier transform for fringe pattern analysis. , 2004, Applied optics.

[6]  Naoki Kuwata,et al.  Deep-learning-based data page classification for holographic memory , 2017, Applied optics.

[7]  J. Wyant,et al.  Basic Wavefront Aberration Theory for Optical Metrology , 1992 .

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

[9]  Qian Kemao,et al.  Windowed Fourier transform for fringe pattern analysis: theoretical analyses. , 2008, Applied optics.

[10]  R. Noll.  Zernike polynomials and atmospheric turbulence , 1976 .

[11]  Adrian Stern,et al.  Speckle denoising in digital holography by nonlocal means filtering. , 2013, Applied optics.

[12]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[13]  Shuai Li,et al.  Lensless computational imaging through deep learning , 2017, ArXiv.

[14]  Ramesh Raskar,et al.  Object classification through scattering media with deep learning on time resolved measurement. , 2017, Optics express.

[15]  Feng Lin,et al.  Fringe pattern denoising using coherence-enhancing diffusion. , 2009, Optics letters.

[16]  Guohai Situ,et al.  Deep-learning-based ghost imaging , 2017, Scientific Reports.