Randomly Disordered Glass-Air Optical Fiber Imaging Based On Deep Learning
Abstract
We demonstrate that images can be reconstructed for objects away from the imaging plane without any distal optics by combining deep neural networks with meter-long glass-air disordered optical fibers. This imaging system is bending-independent.
Publication Date
1-1-2018
Publication Title
Optics InfoBase Conference Papers
Volume
Part F111-SOF 2018
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1364/SOF.2018.SoW1H.2
Copyright Status
Unknown
Socpus ID
85051258540 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/85051258540
STARS Citation
Zhao, Jian; Sun, Yangyang; Zhu, Zheyuan; Antonio-Lopez, Jose Enrique; and Correa, Rodrigo Amezcua, "Randomly Disordered Glass-Air Optical Fiber Imaging Based On Deep Learning" (2018). Scopus Export 2015-2019. 8022.
https://stars.library.ucf.edu/scopus2015/8022