Learning to Sense for Coded Diffraction Imaging

In this paper, we present a framework to learn illumination patterns to improve the quality of signal recovery for coded diffraction imaging. We use an alternating minimization-based phase retrieval method with a fixed number of iterations as the iterative method. We represent the iterative phase re...

Full description

Bibliographic Details
Main Authors: Rakib Hyder, Zikui Cai, M. Salman Asif
Format: Article
Language:English
Published: MDPI AG 2022-12-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/22/24/9964
_version_ 1797455343529230336
author Rakib Hyder
Zikui Cai
M. Salman Asif
author_facet Rakib Hyder
Zikui Cai
M. Salman Asif
author_sort Rakib Hyder
collection DOAJ
description In this paper, we present a framework to learn illumination patterns to improve the quality of signal recovery for coded diffraction imaging. We use an alternating minimization-based phase retrieval method with a fixed number of iterations as the iterative method. We represent the iterative phase retrieval method as an unrolled network with a fixed number of layers where each layer of the network corresponds to a single step of iteration, and we minimize the recovery error by optimizing over the illumination patterns. Since the number of iterations/layers is fixed, the recovery has a fixed computational cost. Extensive experimental results on a variety of datasets demonstrate that our proposed method significantly improves the quality of image reconstruction at a fixed computational cost with illumination patterns learned only using a small number of training images.
first_indexed 2024-03-09T15:52:03Z
format Article
id doaj.art-e9c92d5316b34c018e7013fc0860483c
institution Directory Open Access Journal
issn 1424-8220
language English
last_indexed 2024-03-09T15:52:03Z
publishDate 2022-12-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj.art-e9c92d5316b34c018e7013fc0860483c2023-11-24T17:58:15ZengMDPI AGSensors1424-82202022-12-012224996410.3390/s22249964Learning to Sense for Coded Diffraction ImagingRakib Hyder0Zikui Cai1M. Salman Asif2Department of Electrical and Computer Engineering, University of California, Riverside, CA 92521, USADepartment of Electrical and Computer Engineering, University of California, Riverside, CA 92521, USADepartment of Electrical and Computer Engineering, University of California, Riverside, CA 92521, USAIn this paper, we present a framework to learn illumination patterns to improve the quality of signal recovery for coded diffraction imaging. We use an alternating minimization-based phase retrieval method with a fixed number of iterations as the iterative method. We represent the iterative phase retrieval method as an unrolled network with a fixed number of layers where each layer of the network corresponds to a single step of iteration, and we minimize the recovery error by optimizing over the illumination patterns. Since the number of iterations/layers is fixed, the recovery has a fixed computational cost. Extensive experimental results on a variety of datasets demonstrate that our proposed method significantly improves the quality of image reconstruction at a fixed computational cost with illumination patterns learned only using a small number of training images.https://www.mdpi.com/1424-8220/22/24/9964phase retrievalcoded diffraction imaginglearned sensors
spellingShingle Rakib Hyder
Zikui Cai
M. Salman Asif
Learning to Sense for Coded Diffraction Imaging
Sensors
phase retrieval
coded diffraction imaging
learned sensors
title Learning to Sense for Coded Diffraction Imaging
title_full Learning to Sense for Coded Diffraction Imaging
title_fullStr Learning to Sense for Coded Diffraction Imaging
title_full_unstemmed Learning to Sense for Coded Diffraction Imaging
title_short Learning to Sense for Coded Diffraction Imaging
title_sort learning to sense for coded diffraction imaging
topic phase retrieval
coded diffraction imaging
learned sensors
url https://www.mdpi.com/1424-8220/22/24/9964
work_keys_str_mv AT rakibhyder learningtosenseforcodeddiffractionimaging
AT zikuicai learningtosenseforcodeddiffractionimaging
AT msalmanasif learningtosenseforcodeddiffractionimaging