Share Email Print
cover

Proceedings Paper • new

The importance of physical pre-processors for quantitative phase retrieval under extremely low photon counts
Author(s): Alexandre Goy; Kwabena Arthur; Shuai Li; George Barbastathis
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

In a recent paper [Goy et al., Phys. Rev. Lett. 121, 243902, 2018], we showed that deep neural networks (DNNs) are very efficient solvers for phase retrieval problems, especially when the photon budget is limited. However, the performance of the DNN is strongly conditioned by a preprocessing step that consists in producing a proper initial guess. In this paper, we study the influence of the preprocessing in more details, in particular the choice of the preprocessing operator. We also empirically demonstrate that, for a DenseNet architecture, the performance of the DNN increases with the number of layers up to a point after which it saturates.

Paper Details

Date Published: 4 March 2019
PDF: 8 pages
Proc. SPIE 10887, Quantitative Phase Imaging V, 108870S (4 March 2019); doi: 10.1117/12.2513314
Show Author Affiliations
Alexandre Goy, Massachusetts Institute of Technology (United States)
Kwabena Arthur, Massachusetts Institute of Technology (United States)
Shuai Li, Massachusetts Institute of Technology (United States)
George Barbastathis, Massachusetts Institute of Technology (United States)
Singapore-MIT Alliance for Research and Technology (Singapore)


Published in SPIE Proceedings Vol. 10887:
Quantitative Phase Imaging V
Gabriel Popescu; YongKeun Park, Editor(s)

© SPIE. Terms of Use
Back to Top