Light Propagation Prediction through Multimode Optical Fibers with a Deep Neural Network

Pengfei Fan, Liang Deng, Lei Su

Research output: Chapter in Book or Report/Conference proceedingConference Proceedingpeer-review

3 Citations (Scopus)

Abstract

This work demonstrates a computational method for predicting the light propagation through a single multimode fiber using a deep neural network. The experiment for gathering training and testing data is performed with a digital micro-mirror device that enables the spatial light modulation. The modulated patterns on the device and the captured intensity-only images by the camera form the aligned data pairs. This sufficiently-trained deep neural network frame has very excellent performance for directly inferring the intensity-only output delivered though a multimode fiber. The model is validated by three standards: the mean squared error (MSE), the correlation coefficient (corr) and the structural similarity index (SSIM).

Original languageEnglish
Title of host publicationProceedings of 2018 IEEE 3rd Advanced Information Technology, Electronic and Automation Control Conference, IAEAC 2018
EditorsBing Xu
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1080-1084
Number of pages5
ISBN (Electronic)9781538645086
DOIs
Publication statusPublished - 14 Dec 2018
Externally publishedYes
Event3rd IEEE Advanced Information Technology, Electronic and Automation Control Conference, IAEAC 2018 - Chongqing, China
Duration: 12 Oct 201814 Oct 2018

Publication series

NameProceedings of 2018 IEEE 3rd Advanced Information Technology, Electronic and Automation Control Conference, IAEAC 2018

Conference

Conference3rd IEEE Advanced Information Technology, Electronic and Automation Control Conference, IAEAC 2018
Country/TerritoryChina
CityChongqing
Period12/10/1814/10/18

Keywords

  • computational imaging
  • deep neural network
  • light propagation
  • multimode fibers

Fingerprint

Dive into the research topics of 'Light Propagation Prediction through Multimode Optical Fibers with a Deep Neural Network'. Together they form a unique fingerprint.

Cite this