Deep learning assisted optical wavefront shaping in disordered medium

Wavefront shaping (WFS) has been put forward several years ago to break the limitation caused by optical scattering in inhomogeneous medium, and realize optical focusing in disordered medium like biological tissues. However, usually, with traditional methods, WFS is time consuming and not cost effic...

Full description

Saved in:
Bibliographic Details
Main Authors: Luo, Yunqi, Li, Huanhao, Zhang, Ruochong, Lai, Puxiang, Zheng, Yuanjin
Other Authors: School of Electrical and Electronic Engineering
Format: Conference or Workshop Item
Language:English
Published: 2020
Subjects:
Online Access:https://hdl.handle.net/10356/142286
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-142286
record_format dspace
spelling sg-ntu-dr.10356-1422862020-06-18T06:28:07Z Deep learning assisted optical wavefront shaping in disordered medium Luo, Yunqi Li, Huanhao Zhang, Ruochong Lai, Puxiang Zheng, Yuanjin School of Electrical and Electronic Engineering Adaptive Optics and Wavefront Control for Biological Systems V Engineering::Electrical and electronic engineering Wavefront Shaping Deep Learning Wavefront shaping (WFS) has been put forward several years ago to break the limitation caused by optical scattering in inhomogeneous medium, and realize optical focusing in disordered medium like biological tissues. However, usually, with traditional methods, WFS is time consuming and not cost efficient since it requires long time to obtain the information of the scattering medium. Here we propose the deep learning assisted wavefront shaping, which uses deep neural networks to predict the desired input optical modes that are needed to realize focusing after light passes through a scattering medium. Simulation results show that the pre-trained neural network is able to map output optical modes to input modes. Compared with previous methods which use iterative optimization, our method realizes a focused speckle pattern with the help of deep learning, which will definitely reduce complexity and time spent in optimization. Experiments will be conducted soon. Published version 2020-06-18T06:28:07Z 2020-06-18T06:28:07Z 2019 Conference Paper Luo, Y., Li, H., Zhang, R., Lai, P., & Zheng, Y. (2019). Deep learning assisted optical wavefront shaping in disordered medium. Proceedings of SPIE - Adaptive Optics and Wavefront Control for Biological Systems V, 10886, 1088612-. doi:10.1117/12.2504425 9781510624146 https://hdl.handle.net/10356/142286 10.1117/12.2504425 2-s2.0-85066622575 10886 en Copyright 2019 Society of Photo-Optical Instrumentation Engineers (SPIE). One print or electronic copy may be made for personal use only. Systematic reproduction and distribution, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited. application/pdf
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
topic Engineering::Electrical and electronic engineering
Wavefront Shaping
Deep Learning
spellingShingle Engineering::Electrical and electronic engineering
Wavefront Shaping
Deep Learning
Luo, Yunqi
Li, Huanhao
Zhang, Ruochong
Lai, Puxiang
Zheng, Yuanjin
Deep learning assisted optical wavefront shaping in disordered medium
description Wavefront shaping (WFS) has been put forward several years ago to break the limitation caused by optical scattering in inhomogeneous medium, and realize optical focusing in disordered medium like biological tissues. However, usually, with traditional methods, WFS is time consuming and not cost efficient since it requires long time to obtain the information of the scattering medium. Here we propose the deep learning assisted wavefront shaping, which uses deep neural networks to predict the desired input optical modes that are needed to realize focusing after light passes through a scattering medium. Simulation results show that the pre-trained neural network is able to map output optical modes to input modes. Compared with previous methods which use iterative optimization, our method realizes a focused speckle pattern with the help of deep learning, which will definitely reduce complexity and time spent in optimization. Experiments will be conducted soon.
author2 School of Electrical and Electronic Engineering
author_facet School of Electrical and Electronic Engineering
Luo, Yunqi
Li, Huanhao
Zhang, Ruochong
Lai, Puxiang
Zheng, Yuanjin
format Conference or Workshop Item
author Luo, Yunqi
Li, Huanhao
Zhang, Ruochong
Lai, Puxiang
Zheng, Yuanjin
author_sort Luo, Yunqi
title Deep learning assisted optical wavefront shaping in disordered medium
title_short Deep learning assisted optical wavefront shaping in disordered medium
title_full Deep learning assisted optical wavefront shaping in disordered medium
title_fullStr Deep learning assisted optical wavefront shaping in disordered medium
title_full_unstemmed Deep learning assisted optical wavefront shaping in disordered medium
title_sort deep learning assisted optical wavefront shaping in disordered medium
publishDate 2020
url https://hdl.handle.net/10356/142286
_version_ 1681059284394180608