Deep-Learning-Based Imaging Through Glass-Air Disordered Fiber With Transverse Anderson Localization

Creator

Jian Zhao, University of Central Florida
Yangyang Sun, University of Central Florida
Zheyuan Zhu, University of Central Florida
Donghui Zheng, University of Central Florida
Jose Enrique Antonio-Lopez, University of Central Florida

Abstract

We demonstrate for the first time that deep neural networks (DNNs) can be trained to recover images transported through a 90 cm-long silica-air disordered optical fiber at variable working distances without any distal optics.

Publication Date

1-1-2018

Publication Title

Optics InfoBase Conference Papers

Volume

Part F94-CLEO_SI 2018

Document Type

Article; Proceedings Paper

Personal Identifier

scopus

DOI Link

https://doi.org/10.1364/CLEO_SI.2018.STu3K.3

Copyright Status

Unknown

Socpus ID

85048963543 (Scopus)

Source API URL

https://api.elsevier.com/content/abstract/scopus_id/85048963543

STARS Citation

Zhao, Jian; Sun, Yangyang; Zhu, Zheyuan; Zheng, Donghui; and Antonio-Lopez, Jose Enrique, "Deep-Learning-Based Imaging Through Glass-Air Disordered Fiber With Transverse Anderson Localization" (2018). Scopus Export 2015-2019. 8083.
https://stars.library.ucf.edu/scopus2015/8083