Share Email Print
cover

Proceedings Paper • new

Deep neural networks for seeing through multimode fibers
Format Member Price Non-Member Price
PDF $17.00 $21.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Image delivery through multimode fibers (MMFs) suffers from modal scrambling which results in a speckle pattern at the fiber output. In this work, we use Deep Neural Networks (DNNs) for recovery and/or classification of the input image from the intensity-only images of the speckle patterns at the distal end of the fiber. We train the DNNs using 16,000 images of handwritten digits of the MNIST database and we test the accuracy of classification and reconstruction on another 2,000 new digits. Very positive results and robustness were observed for up to 1 km long MMF showing 90% reconstruction fidelity. The classification accuracy of the system for different inputs (phase-only, amplitude-only, hologram intensity etc.) to the DNN classifier was also tested.

Paper Details

Date Published: 4 March 2019
PDF: 6 pages
Proc. SPIE 10889, High-Speed Biomedical Imaging and Spectroscopy IV, 108891A (4 March 2019); doi: 10.1117/12.2509934
Show Author Affiliations
Eirini Kakkava, Ecole Polytechnique Fédérale de Lausanne (Switzerland)
Navid Borhani, Ecole Polytechnique Fédérale de Lausanne (Switzerland)
Christophe Moser, Ecole Polytechnique Fédérale de Lausanne (Switzerland)
Demetri Psaltis, Ecole Polytechnique Fédérale de Lausanne (Switzerland)


Published in SPIE Proceedings Vol. 10889:
High-Speed Biomedical Imaging and Spectroscopy IV
Kevin K. Tsia; Keisuke Goda, Editor(s)

© SPIE. Terms of Use
Back to Top