Bending-Independent Imaging Through Glass-Air Disordered Fiber Based On Deep Learning

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 a bending-independent imaging system for the first time by combining deep neural networks (DNNs) and a meter-long silica-air disordered optical fiber. High-quality artifact-free images can be reconstructed from the transported raw images.

Publication Date

1-1-2018

Publication Title

Optics InfoBase Conference Papers

Volume

Part F99-COSI 2018

Document Type

Article; Proceedings Paper

Personal Identifier

scopus

DOI Link

https://doi.org/10.1364/COSI.2018.CW3B.6

Copyright Status

Unknown

Socpus ID

85051269020 (Scopus)

Source API URL

https://api.elsevier.com/content/abstract/scopus_id/85051269020

STARS Citation

Zhao, Jian; Sun, Yangyang; Zhu, Zheyuan; Zheng, Donghui; and Antonio-Lopez, Jose Enrique, "Bending-Independent Imaging Through Glass-Air Disordered Fiber Based On Deep Learning" (2018). Scopus Export 2015-2019. 8018.
https://stars.library.ucf.edu/scopus2015/8018