Machine learning assisted holography

Computer-generated holography (CGH) has enabled the formation of arbitrary images through complex spatial light modulation. The optimization of spatial light modulators (SLMs) and diffractive optical elements (DOEs) is aimed to solve the well-known phase retrieval problem. This paper proposes a physically constrained artificial neural network (ANN) designed to solve the phase retrieval problem for CGH. We show that through careful selection of model structural parameters and by limiting the scope of model optimization, we can encode Fresnel Diffraction equations directly into an ANN. We train the proposed model to overfit to a single image, i.e., the model finds the SLM phase delays required to produce the desired image. The proposed model performs well with outputs that qualitatively compare well with ideal images. The method proposed in this work holds value for those who require confidence that their machine learning techniques are physically realizable.

[1]  Yifan Peng,et al.  Neural Holography , 2020, SIGGRAPH Emerging Technologies.

[2]  Wolfgang Osten,et al.  Phase retrieval microscopy for quantitative phase-contrast imaging , 2004 .

[3]  Yen-Wei Chen,et al.  Optimization of computer-generated holograms by an artificial neural network , 1998, 1998 Second International Conference. Knowledge-Based Intelligent Electronic Systems. Proceedings KES'98 (Cat. No.98EX111).

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

[5]  J. G. Walker.  The Phase Retrieval Problem , 1981 .

[6]  J. Goodman.  Introduction to Fourier optics , 1969 .

[7]  Amina Adadi,et al.  Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI) , 2018, IEEE Access.

[8]  S. Bernet,et al.  What spatial light modulators can do for optical microscopy , 2011 .

[9]  Pavel A. Cheremkhin,et al.  Machine learning methods for digital holography and diffractive optics , 2020 .

[10]  Brian D. Rigling,et al.  Phase Retrieval for Radar Waveform Optimization , 2012, IEEE Transactions on Aerospace and Electronic Systems.

[11]  Sandeep Subramanian,et al.  Deep Complex Networks , 2017, ICLR.

[13]  J R Fienup,et al.  Phase retrieval algorithms: a comparison. , 1982, Applied optics.

[14]  Rick P. Millane,et al.  Phase retrieval in crystallography and optics , 1990 .

[15]  Natalia Gimelshein,et al.  PyTorch: An Imperative Style, High-Performance Deep Learning Library , 2019, NeurIPS.

[16]  Jun Tanida,et al.  Deep-learning-generated holography. , 2018, Applied optics.

[17]  Filip Karlo Dosilovic,et al.  Explainable artificial intelligence: A survey , 2018, 2018 41st International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO).

[18]  Hao Wang,et al.  Off‐Axis Holography with Uniform Illumination via 3D Printed Diffractive Optical Elements , 2019, Advanced Optical Materials.

[19]  Dieter Basler.  Holographic Optical Elements , 1989, Other Conferences.

[20]  Michael C Roggemann,et al.  Digital simulation of scalar optical diffraction: revisiting chirp function sampling criteria and consequences. , 2009, Applied optics.