Randomness assisted in-line holography with deep learning.
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
07 Jul 2023
07 Jul 2023
Historique:
received:
02
04
2023
accepted:
28
06
2023
medline:
10
7
2023
pubmed:
8
7
2023
entrez:
7
7
2023
Statut:
epublish
Résumé
We propose and demonstrate a holographic imaging scheme exploiting random illuminations for recording hologram and then applying numerical reconstruction and twin image removal. We use an in-line holographic geometry to record the hologram in terms of the second-order correlation and apply the numerical approach to reconstruct the recorded hologram. This strategy helps to reconstruct high-quality quantitative images in comparison to the conventional holography where the hologram is recorded in the intensity rather than the second-order intensity correlation. The twin image issue of the in-line holographic scheme is resolved by an unsupervised deep learning based method using an auto-encoder scheme. Proposed learning technique leverages the main characteristic of autoencoders to perform blind single-shot hologram reconstruction, and this does not require a dataset of samples with available ground truth for training and can reconstruct the hologram solely from the captured sample. Experimental results are presented for two objects, and a comparison of the reconstruction quality is given between the conventional inline holography and the one obtained with the proposed technique.
Identifiants
pubmed: 37419990
doi: 10.1038/s41598-023-37810-w
pii: 10.1038/s41598-023-37810-w
pmc: PMC10329003
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
10986Subventions
Organisme : Science and Engineering Research Board
ID : CORE/2019/000026
Informations de copyright
© 2023. The Author(s).
Références
Opt Lett. 2012 Oct 15;37(20):4212-4
pubmed: 23073414
Phys Rev Lett. 2007 Jun 8;98(23):233901
pubmed: 17677906
Opt Express. 2010 Jun 21;18(13):14159-64
pubmed: 20588549
Opt Express. 2021 Oct 25;29(22):35078-35118
pubmed: 34808951
Opt Express. 2014 Apr 7;22(7):7694-701
pubmed: 24718145
Proc Natl Acad Sci U S A. 2005 Sep 13;102(37):13081-6
pubmed: 16141335
Light Sci Appl. 2022 Aug 16;11(1):254
pubmed: 35970839
Chem Rev. 2017 Dec 13;117(23):13890-13908
pubmed: 29125755
Nano Lett. 2022 Mar 23;22(6):2194-2201
pubmed: 35240776
Microscopy (Oxf). 2018 Apr 1;67(2):55-67
pubmed: 29471371
Sci Rep. 2016 Apr 21;6:24681
pubmed: 27098438
J Microsc. 2000 May;198(Pt 2):82-7
pubmed: 10810003
Opt Express. 2006 Jun 12;14(12):5168-77
pubmed: 19516681
Opt Express. 2015 Aug 10;23(16):20916-25
pubmed: 26367944
Phys Rev Lett. 2011 May 13;106(19):193905
pubmed: 21668161
Opt Lett. 1997 Aug 15;22(16):1268-70
pubmed: 18185816
Appl Opt. 2019 Mar 20;58(9):2350-2357
pubmed: 31044932
Opt Lett. 1998 Aug 1;23(15):1221-3
pubmed: 18087480
Light Sci Appl. 2016 Mar 25;5(3):e16048
pubmed: 30167151
Appl Opt. 2006 Feb 10;45(5):968-74
pubmed: 16512540
Opt Express. 2005 Aug 8;13(16):6073-8
pubmed: 19498615
Nature. 1948 May 15;161(4098):777
pubmed: 18860291
Opt Lett. 2013 Apr 15;38(8):1328-30
pubmed: 23595474
Opt Express. 2009 Jul 20;17(15):12285-92
pubmed: 19654630
Nat Commun. 2019 Mar 21;10(1):1304
pubmed: 30898998
Appl Opt. 1982 Aug 1;21(15):2758-69
pubmed: 20396114
Biomed Opt Express. 2017 Nov 28;8(12):5776-5793
pubmed: 29296504
Sci Rep. 2013;3:1909
pubmed: 23714766
Opt Lett. 2013 Mar 1;38(5):682-4
pubmed: 23455264
Opt Express. 2015 Dec 28;23(26):33170-83
pubmed: 26831985
Light Sci Appl. 2018 Feb 23;7:17141
pubmed: 30839514
Ultramicroscopy. 2004 Dec;102(1):37-49
pubmed: 15556699
Appl Opt. 2006 May 1;45(13):2995-3002
pubmed: 16639447
Phys Rev Lett. 1988 Nov 14;61(20):2328-2331
pubmed: 10039084
Opt Express. 2012 Dec 31;20(28):29210-6
pubmed: 23388746
Opt Lett. 2019 Dec 1;44(23):5711-5714
pubmed: 31774760
Opt Lett. 2023 Mar 15;48(6):1347-1350
pubmed: 36946924
Appl Opt. 2008 Feb 1;47(4):A52-61
pubmed: 18239699
Phys Rev Lett. 2018 Aug 31;121(9):093902
pubmed: 30230890
J Opt Soc Am A Opt Image Sci Vis. 2019 Dec 1;36(12):D31-D40
pubmed: 31873366