Share Email Print
cover

Proceedings Paper

Alternation of inverse problem and deep learning approaches for phase unwrapping in lens-free microscopy (Conference Presentation)
Author(s): Cédric Allier; Lionel Hervé; Dorothée Kraemer; Olivier Cioni; Mathilde Menneteau; Ondrej Mandula; Sophie Morales

Paper Abstract

Lens-free microscopy aims at recovering sample image from diffraction measurements. The acquisitions are usually processed with an inverse problem approach. Recently, deep learning has been used to further improve phase retrieval results. Here, we propose to alternate iteratively between the two algorithms, to improve the reconstruction results without losing data fidelity. We validated this method for the phase image recovery of floating cells sample at large density acquired by means of lens-free microscopy. This is a challenging case with a lot of phase wrapping artefacts that has never been successfully solved using inverse problem approaches only.

Paper Details

Date Published: 11 March 2020
PDF
Proc. SPIE 11249, Quantitative Phase Imaging VI, 1124914 (11 March 2020); doi: 10.1117/12.2544812
Show Author Affiliations
Cédric Allier, Lab. d'Electronique de Technologie de l'Information (France)
Lionel Hervé, Lab. d'Electronique de Technologie de l'Information (France)
Dorothée Kraemer, Lab. d'Electronique de Technologie de l'Information (France)
Olivier Cioni, Lab. d'Electronique de Technologie de l'Information (France)
Mathilde Menneteau, Lab. d'Electronique de Technologie de l'Information (France)
Ondrej Mandula, Lab. d'Electronique de Technologie de l'Information (France)
Sophie Morales, Lab. d'Electronique de Technologie de l'Information (France)


Published in SPIE Proceedings Vol. 11249:
Quantitative Phase Imaging VI
Yang Liu; Gabriel Popescu; YongKeun Park, Editor(s)

© SPIE. Terms of Use
Back to Top
PREMIUM CONTENT
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?
close_icon_gray