Deep convolutional neural network-based lensless quantitative phase retrieval

Igor Shevkunov; Jarkko Kilpeläinen; Karen Eguiazarian

doi:10.1117/12.2581428

Deep convolutional neural network-based lensless quantitative phase retrieval

Igor Shevkunov, Jarkko Kilpeläinen, Karen Eguiazarian

Computing Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

14 Downloads (Pure)

Abstract

In this paper, we employ a deep convolutional neural network for the solution of the phase retrieval problem in a lensless optical system from a single observation. We utilize U-net-like structured DCNN to reconstruct phase from the amplitude images at the sensor plane, and after applying computational backpropagation, the complex objects’ amplitude is reconstructed at the object plane. Results are demonstrated by simulation experiments.

Original language	English
Title of host publication	Quantitative Phase Imaging VII
Editors	Yang Liu, Gabriel Popescu, YongKeun Park
Publisher	SPIE
ISBN (Electronic)	9781510641426
ISBN (Print)	9781510641419
DOIs	https://doi.org/10.1117/12.2581428
Publication status	Published - 2021
Publication type	A4 Article in conference proceedings
Event	Quantitative Phase Imaging - Virtual, Online, United States Duration: 6 Mar 2021 → 11 Mar 2021

Publication series

Name	Progress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume	11653
ISSN (Print)	1605-7422
ISSN (Electronic)	2410-9045

Conference

Conference	Quantitative Phase Imaging
Country/Territory	United States
City	Virtual, Online
Period	6/03/21 → 11/03/21

Publication forum classification

Publication forum level 1

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
Atomic and Molecular Physics, and Optics
Biomaterials
Radiology Nuclear Medicine and imaging

Access to Document

10.1117/12.2581428

2021 Deep convolutional neural network-based lensless quantitative phase retrieval_SPIE_proc
This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.
Final published version, 1.04 MBLicence: Unspecified

https://urn.fi/URN:NBN:fi:tuni-202210267890Licence: Unspecified

Cite this

@inproceedings{94eb4271151e43819b155c9a7eb8278a,

title = "Deep convolutional neural network-based lensless quantitative phase retrieval",

abstract = "In this paper, we employ a deep convolutional neural network for the solution of the phase retrieval problem in a lensless optical system from a single observation. We utilize U-net-like structured DCNN to reconstruct phase from the amplitude images at the sensor plane, and after applying computational backpropagation, the complex objects{\textquoteright} amplitude is reconstructed at the object plane. Results are demonstrated by simulation experiments.",

author = "Igor Shevkunov and Jarkko Kilpel{\"a}inen and Karen Eguiazarian",

note = "JUFOID=65546 Funding Information: Jane and Aatos Erkko Foundation and Finland Centennial Foundation funded Computational Imaging without Lens (CIWIL) project. Publisher Copyright: {\textcopyright} 2021 SPIE.; Quantitative Phase Imaging ; Conference date: 06-03-2021 Through 11-03-2021",

year = "2021",

doi = "10.1117/12.2581428",

language = "English",

isbn = "9781510641419",

series = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",

publisher = "SPIE",

editor = "Yang Liu and Gabriel Popescu and YongKeun Park",

booktitle = "Quantitative Phase Imaging VII",

address = "United States",

}

Shevkunov, I, Kilpeläinen, J & Eguiazarian, K 2021, Deep convolutional neural network-based lensless quantitative phase retrieval. in Y Liu, G Popescu & Y Park (eds), Quantitative Phase Imaging VII., 116531F, Progress in Biomedical Optics and Imaging - Proceedings of SPIE, vol. 11653, SPIE, Quantitative Phase Imaging, Virtual, Online, United States, 6/03/21. https://doi.org/10.1117/12.2581428

Deep convolutional neural network-based lensless quantitative phase retrieval. / Shevkunov, Igor; Kilpeläinen, Jarkko; Eguiazarian, Karen.
Quantitative Phase Imaging VII. ed. / Yang Liu; Gabriel Popescu; YongKeun Park. SPIE, 2021. 116531F (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 11653).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Deep convolutional neural network-based lensless quantitative phase retrieval

AU - Shevkunov, Igor

AU - Kilpeläinen, Jarkko

AU - Eguiazarian, Karen

PY - 2021

Y1 - 2021

N2 - In this paper, we employ a deep convolutional neural network for the solution of the phase retrieval problem in a lensless optical system from a single observation. We utilize U-net-like structured DCNN to reconstruct phase from the amplitude images at the sensor plane, and after applying computational backpropagation, the complex objects’ amplitude is reconstructed at the object plane. Results are demonstrated by simulation experiments.

AB - In this paper, we employ a deep convolutional neural network for the solution of the phase retrieval problem in a lensless optical system from a single observation. We utilize U-net-like structured DCNN to reconstruct phase from the amplitude images at the sensor plane, and after applying computational backpropagation, the complex objects’ amplitude is reconstructed at the object plane. Results are demonstrated by simulation experiments.

U2 - 10.1117/12.2581428

DO - 10.1117/12.2581428

M3 - Conference contribution

AN - SCOPUS:85107919468

SN - 9781510641419

T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

BT - Quantitative Phase Imaging VII

A2 - Liu, Yang

A2 - Popescu, Gabriel

A2 - Park, YongKeun

PB - SPIE

T2 - Quantitative Phase Imaging

Y2 - 6 March 2021 through 11 March 2021

ER -

Deep convolutional neural network-based lensless quantitative phase retrieval

Abstract

Publication series

Conference

Publication forum classification

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this