Dense-U-net: Dense encoder–decoder network for holographic imaging of 3D particle fields

Digital holographic imaging is able to reconstruct phase and three-dimensional (3D) information of an object from a one-shot two-dimensional (2D) lensless hologram. A dense encoder–decoder network, called Dense-U-net, is proposed to realize the reconstruction of a 3D particle field. The radii and 3D...

Full description

Saved in:
Bibliographic Details
Published in:Optics communications Vol. 493; p. 126970
Main Authors: Wu, Yufeng, Wu, Jiachen, Jin, Shangzhong, Cao, Liangcai, Jin, Guofan
Format: Journal Article
Language:English
Published: Elsevier B.V 15.08.2021
Subjects:
ISSN:0030-4018, 1873-0310
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Digital holographic imaging is able to reconstruct phase and three-dimensional (3D) information of an object from a one-shot two-dimensional (2D) lensless hologram. A dense encoder–decoder network, called Dense-U-net, is proposed to realize the reconstruction of a 3D particle field. The radii and 3D coordinates of the particles are encoded into a 2D grayscale image as the ground truth. The 2D hologram was served as the input of the network. A Dense_Block is designed and added to the encoder and decoder of the traditional U-net model. Each layer takes the inputs from all previous layers and passes its own feature map to all subsequent layers. Thus, as the diffraction is distributed throughout the entire hologram, both the features with high signal-to-noise ratio at the center of the particle and the diffraction features with low signal-to-noise ratio around the particle can be learned, thereby facilitating the full characterization of the particles. Using the specially designed dense connection module, network training can be accomplished with fewer parameters and faster speeds. •A dense encoder–decoder network is proposed to realize reconstruction of 3D particle field.•The Dense-U-net network needs few training parameters and short training time.•A new way is proposed to generate the dataset for digital holographic networks.
AbstractList Digital holographic imaging is able to reconstruct phase and three-dimensional (3D) information of an object from a one-shot two-dimensional (2D) lensless hologram. A dense encoder–decoder network, called Dense-U-net, is proposed to realize the reconstruction of a 3D particle field. The radii and 3D coordinates of the particles are encoded into a 2D grayscale image as the ground truth. The 2D hologram was served as the input of the network. A Dense_Block is designed and added to the encoder and decoder of the traditional U-net model. Each layer takes the inputs from all previous layers and passes its own feature map to all subsequent layers. Thus, as the diffraction is distributed throughout the entire hologram, both the features with high signal-to-noise ratio at the center of the particle and the diffraction features with low signal-to-noise ratio around the particle can be learned, thereby facilitating the full characterization of the particles. Using the specially designed dense connection module, network training can be accomplished with fewer parameters and faster speeds. •A dense encoder–decoder network is proposed to realize reconstruction of 3D particle field.•The Dense-U-net network needs few training parameters and short training time.•A new way is proposed to generate the dataset for digital holographic networks.
ArticleNumber 126970
Author Wu, Yufeng
Cao, Liangcai
Wu, Jiachen
Jin, Shangzhong
Jin, Guofan
Author_xml – sequence: 1
  givenname: Yufeng
  surname: Wu
  fullname: Wu, Yufeng
  organization: College of Optical and Electronic Technology, China Jiliang University, Hangzhou, Zhejiang 310018, China
– sequence: 2
  givenname: Jiachen
  surname: Wu
  fullname: Wu, Jiachen
  organization: State Key Laboratory of Precision Measurement Technology and Instruments, Department of Precision Instruments, Tsinghua University, Beijing 100084, China
– sequence: 3
  givenname: Shangzhong
  surname: Jin
  fullname: Jin, Shangzhong
  email: jinsz@cjlu.edu.cn
  organization: College of Optical and Electronic Technology, China Jiliang University, Hangzhou, Zhejiang 310018, China
– sequence: 4
  givenname: Liangcai
  surname: Cao
  fullname: Cao, Liangcai
  email: clc@tsinghua.edu.cn, P1804085245@cjlu.edu.cn
  organization: State Key Laboratory of Precision Measurement Technology and Instruments, Department of Precision Instruments, Tsinghua University, Beijing 100084, China
– sequence: 5
  givenname: Guofan
  surname: Jin
  fullname: Jin, Guofan
  organization: State Key Laboratory of Precision Measurement Technology and Instruments, Department of Precision Instruments, Tsinghua University, Beijing 100084, China
BookMark eNqFkEtOwzAQhi1UJNrCDVj4AgnjOA-nCyTU8pKQ2NANG8t1xq1LGkeOBWLHHbghJyFtWLGA1czo1zea-SZk1LgGCTlnEDNg-cU2dm3QbhcnkLCYJXlZwBEZM1HwCDiDERkDcIhSYOKETLpuCwAs5WJMnhfYdBgtowbDjB4Gio12Ffqvj88KDx3twzfnX6hxnm5c7dZetRurqd2ptW3W1BnKF7RVPlhdIzUW66o7JcdG1R2e_dQpWd5cP83voofH2_v51UOkOeQhKnSmi0KttBEISSYyFFoYxlWpBUtVWvYxwzxnfKXSQiW8SnlZJStjMsFEJviUpMNe7V3XeTSy9f1h_l0ykHs_cisHP3LvRw5-emz2C9M2qGBdE7yy9X_w5QBj_9irRS87bXtvWFmPOsjK2b8XfAPaC4b6
CitedBy_id crossref_primary_10_25259_JKSUS_280_2024
crossref_primary_10_1016_j_apt_2023_104201
crossref_primary_10_1016_j_optlaseng_2025_109170
crossref_primary_10_1007_s10489_025_06887_3
crossref_primary_10_1117_1_APN_1_1_014001
crossref_primary_10_1088_1402_4896_ad67ac
crossref_primary_10_1177_08953996251355806
crossref_primary_10_7717_peerj_cs_1515
crossref_primary_10_1109_LPT_2022_3222814
crossref_primary_10_1109_JSTARS_2024_3375313
crossref_primary_10_1016_j_optlaseng_2022_106989
crossref_primary_10_1016_j_pdpdt_2024_104030
crossref_primary_10_3788_IRLA20240490
crossref_primary_10_1016_j_optlaseng_2024_108401
crossref_primary_10_1109_TGRS_2025_3607732
crossref_primary_10_1016_j_optcom_2022_128018
crossref_primary_10_1016_j_optlaseng_2024_108201
crossref_primary_10_3389_fphy_2021_816158
crossref_primary_10_1002_adpr_202300120
crossref_primary_10_1109_TII_2022_3151781
crossref_primary_10_3390_photonics12070702
crossref_primary_10_1121_10_0026438
crossref_primary_10_1007_s11227_025_07590_3
crossref_primary_10_1063_5_0279042
crossref_primary_10_3390_electronics13030617
crossref_primary_10_1093_mmy_myae050
crossref_primary_10_1109_ACCESS_2024_3496923
crossref_primary_10_1016_j_optlastec_2022_108602
crossref_primary_10_3390_electronics14091789
crossref_primary_10_1016_j_measurement_2022_111531
crossref_primary_10_3390_app132011430
crossref_primary_10_1364_AO_477427
crossref_primary_10_1016_j_optlastec_2025_112622
crossref_primary_10_1007_s40846_023_00828_6
crossref_primary_10_1109_TETCI_2023_3306250
crossref_primary_10_1109_TII_2024_3431072
crossref_primary_10_1016_j_compbiomed_2023_107584
crossref_primary_10_1364_OE_562852
crossref_primary_10_3389_fphy_2022_1048577
crossref_primary_10_1007_s00707_025_04413_7
crossref_primary_10_1088_1361_6501_adabff
crossref_primary_10_3390_s24092723
crossref_primary_10_1016_j_fmre_2024_03_019
crossref_primary_10_3390_app13106125
crossref_primary_10_1177_14727978251361852
crossref_primary_10_1007_s42242_022_00226_y
crossref_primary_10_1016_j_optlastec_2025_113344
crossref_primary_10_1080_17455030_2023_2181644
crossref_primary_10_3389_fmed_2023_1190659
Cites_doi 10.1364/OE.27.013581
10.1109/CVPR.2017.243
10.1364/OL.44.004765
10.1007/978-3-030-01234-2_49
10.1016/j.optlaseng.2018.12.001
10.1364/BOE.10.004276
10.1109/CVPR.2017.632
10.1038/s41598-020-65716-4
10.1364/OPTICA.5.000704
10.1364/OE.27.018069
10.1364/OPTICA.6.000921
10.1364/BOE.8.004466
10.1109/CVPR.2016.90
10.1364/BOE.399020
10.1364/AO.58.00G332
10.1364/OE.379480
10.1364/OL.395445
10.1364/OE.383350
10.1364/OE.26.015221
10.1109/TIP.2003.819861
10.1038/lsa.2017.141
10.1016/j.optcom.2018.12.081
10.1109/ACCESS.2019.2914873
10.1364/OE.25.015043
10.1364/AO.58.00A202
10.1145/3329784
10.1364/AO.58.001900
10.1364/OE.23.025440
10.1038/s41377-020-0255-6
ContentType Journal Article
Copyright 2021
Copyright_xml – notice: 2021
DBID AAYXX
CITATION
DOI 10.1016/j.optcom.2021.126970
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Physics
EISSN 1873-0310
ExternalDocumentID 10_1016_j_optcom_2021_126970
S0030401821002200
GroupedDBID --K
--M
-~X
.~1
0R~
123
1B1
1RT
1~.
1~5
4.4
457
4G.
53G
5VS
7-5
71M
8P~
9JN
AABNK
AABXZ
AACTN
AAEDT
AAEDW
AAEPC
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAXUO
ABFNM
ABJNI
ABMAC
ABNEU
ABXRA
ABYKQ
ACDAQ
ACFVG
ACGFS
ACNCT
ACRLP
ADBBV
ADEZE
AEBSH
AEKER
AENEX
AEZYN
AFKWA
AFRZQ
AFTJW
AGHFR
AGUBO
AGYEJ
AHHHB
AIEXJ
AIKHN
AITUG
AIVDX
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AXJTR
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EFLBG
EO8
EO9
EP2
EP3
F5P
FDB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
IHE
J1W
KOM
LY7
M38
M41
MAGPM
MO0
N9A
O-L
O9-
OAUVE
OGIMB
OZT
P-8
P-9
P2P
PC.
Q38
RNS
ROL
RPZ
SDF
SDG
SDP
SES
SPC
SPCBC
SPD
SSM
SSQ
SSZ
T5K
TN5
XPP
ZMT
~02
~G-
29N
6TJ
9DU
AAQXK
AATTM
AAXKI
AAYWO
AAYXX
ABDPE
ABWVN
ABXDB
ACLOT
ACNNM
ACRPL
ACVFH
ADCNI
ADIYS
ADMUD
ADNMO
AEIPS
AETEA
AEUPX
AFFNX
AFJKZ
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
APXCP
ASPBG
AVWKF
AZFZN
BBWZM
CITATION
EFKBS
EJD
F0J
FEDTE
FGOYB
G-2
HMV
HVGLF
HZ~
MVM
NDZJH
R2-
SET
SEW
SPG
WUQ
ZY4
~HD
ID FETCH-LOGICAL-c306t-7c5c77abcf8e02585e8c8f13a9c814a495c71e6613ba47a23d439d2bff5818583
ISICitedReferencesCount 72
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000653031900010&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0030-4018
IngestDate Tue Nov 18 21:44:54 EST 2025
Sat Nov 29 07:26:24 EST 2025
Fri Feb 23 02:45:35 EST 2024
IsPeerReviewed true
IsScholarly true
Keywords Deep learning
Digital holography
Dense-U-net
Image reconstruction
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c306t-7c5c77abcf8e02585e8c8f13a9c814a495c71e6613ba47a23d439d2bff5818583
ParticipantIDs crossref_primary_10_1016_j_optcom_2021_126970
crossref_citationtrail_10_1016_j_optcom_2021_126970
elsevier_sciencedirect_doi_10_1016_j_optcom_2021_126970
PublicationCentury 2000
PublicationDate 2021-08-15
PublicationDateYYYYMMDD 2021-08-15
PublicationDate_xml – month: 08
  year: 2021
  text: 2021-08-15
  day: 15
PublicationDecade 2020
PublicationTitle Optics communications
PublicationYear 2021
Publisher Elsevier B.V
Publisher_xml – name: Elsevier B.V
References Ghosh, Das, Das, Maulik (b9) 2019; 52
Li, Dong, Du, Mu (b35) 2019; 7
Ioffe, Szegedy (b28) 2015
Wang, Bovik, Sheikh, Simoncelli (b41) 2004; 13
Jaferzadeh, Hwang, Moon, Javidi (b17) 2019; 10
Kingma, Ba (b40) 2014
Shao, Mallery, Kumar, Hong (b4) 2020; 28
O’Connor, Anand, Andemariam, Javidi (b15) 2020; 11
Pitkäaho, Manninen, Naughton (b16) 2019; 58
Wu, Jin, Cao (b30) 2020
Liu, Lian, Xu (b19) 2019; 115
Zeng, So, Lam (b20) 2020; 28
Wang, Kemao, Di, Zhao (b21) 2020; 45
Hannel, Abdulali, O’Brien, Grier (b7) 2018; 26
Zou, Shi, Guo, Ye (b10) 2019
Zhao, Cao, Zhang, Kong, Jin (b27) 2015; 23
Chollet (b39) 2015
Luo, Yurt, Stahl, Lambrechts, Reumers, Braeken, Lagae (b23) 2019; 27
G. Huang, Z. Liu, L.V.D. Maaten, K.Q. Weinberger, densely connected convolutional networks, in: Proceedings of the IEEE conference on computer vision and pattern recognition 2017, pp. 4700–4708.
K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2016, pp. 770–778.
Barbastathis, Ozcan, Situ (b11) 2019; 6
Mallery, Hong (b6) 2019; 27
Wang, Dou, Qian, Di, Zhao (b14) 2019; 44
Yi, Moon, Javidi (b1) 2017; 8
V.Q.E. Group, Final report from the video quality experts group on the validation of objective models of video quality assessment, VQEG meeting, Ottawa, Canada, March, 2000.
Wu, Li, Yao, Wu, Lin, Chen, Cen (b2) 2019; 58
Liu, de Haan, Rivenson, Wei, Zeng, Zhang, Ozcan (b36) 2019; 9
Souza, Freire, Santos (b24) 2019; 437
Hussain, Noyan, Woyessa, Marín, Martinez, Mahdi, Finazzi, Hazlehurst, Hunter, Coll (b3) 2020; 9
Ramachandran, Zoph, Le (b33) 2017
Pont-Tuset, Perazzi, Caelles, Arbeláez, Sorkine-Hornung, Gool (b34) 2017
L.-C. Chen, Y. Zhu, G. Papandreou, F. Schroff, H. Adam, Encoder–decoder with atrous separable convolution for semantic image segmentation, in: Proceedings of the European Conference on Computer Vision (ECCV) 2018, 801–818.
Wu, Rivenson, Zhang, Wei, Günaydin, Lin, Ozcan (b12) 2018; 5
Goodman (b31) 2005
P. Isola, J.-Y. Zhu, T. Zhou, A.A. Efros, Image-to-image translation with conditional adversarial networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2017, pp. 1125–1134.
Go, Lee, You, Lee (b22) 2020; 10
Ronneberger, Fischer, Brox (b25) 2015
Shimobaba, Takahashi, Yamamoto, Endo, Shiraki, Nishitsuji, Hoshikawa, Kakue, Ito (b5) 2019; 58
Goodfellow, Bengio, Courville (b32) 2016
Shimobaba, Ito (b8) 2019
Nguyen, Bui, Lam, Raub, Chang, Nehmetallah (b18) 2017; 25
Rivenson, Zhang, Günaydın, Teng, Ozcan (b13) 2018; 7
Zou (10.1016/j.optcom.2021.126970_b10) 2019
Goodfellow (10.1016/j.optcom.2021.126970_b32) 2016
Nguyen (10.1016/j.optcom.2021.126970_b18) 2017; 25
10.1016/j.optcom.2021.126970_b26
Liu (10.1016/j.optcom.2021.126970_b19) 2019; 115
Barbastathis (10.1016/j.optcom.2021.126970_b11) 2019; 6
Li (10.1016/j.optcom.2021.126970_b35) 2019; 7
Yi (10.1016/j.optcom.2021.126970_b1) 2017; 8
10.1016/j.optcom.2021.126970_b29
Zhao (10.1016/j.optcom.2021.126970_b27) 2015; 23
O’Connor (10.1016/j.optcom.2021.126970_b15) 2020; 11
Rivenson (10.1016/j.optcom.2021.126970_b13) 2018; 7
Go (10.1016/j.optcom.2021.126970_b22) 2020; 10
Ioffe (10.1016/j.optcom.2021.126970_b28) 2015
Wang (10.1016/j.optcom.2021.126970_b41) 2004; 13
Souza (10.1016/j.optcom.2021.126970_b24) 2019; 437
Zeng (10.1016/j.optcom.2021.126970_b20) 2020; 28
Mallery (10.1016/j.optcom.2021.126970_b6) 2019; 27
Shimobaba (10.1016/j.optcom.2021.126970_b5) 2019; 58
Ghosh (10.1016/j.optcom.2021.126970_b9) 2019; 52
10.1016/j.optcom.2021.126970_b42
Wu (10.1016/j.optcom.2021.126970_b2) 2019; 58
Liu (10.1016/j.optcom.2021.126970_b36) 2019; 9
Wang (10.1016/j.optcom.2021.126970_b14) 2019; 44
10.1016/j.optcom.2021.126970_b38
Pont-Tuset (10.1016/j.optcom.2021.126970_b34) 2017
10.1016/j.optcom.2021.126970_b37
Wang (10.1016/j.optcom.2021.126970_b21) 2020; 45
Shimobaba (10.1016/j.optcom.2021.126970_b8) 2019
Ramachandran (10.1016/j.optcom.2021.126970_b33) 2017
Ronneberger (10.1016/j.optcom.2021.126970_b25) 2015
Wu (10.1016/j.optcom.2021.126970_b12) 2018; 5
Kingma (10.1016/j.optcom.2021.126970_b40) 2014
Hussain (10.1016/j.optcom.2021.126970_b3) 2020; 9
Jaferzadeh (10.1016/j.optcom.2021.126970_b17) 2019; 10
Pitkäaho (10.1016/j.optcom.2021.126970_b16) 2019; 58
Shao (10.1016/j.optcom.2021.126970_b4) 2020; 28
Goodman (10.1016/j.optcom.2021.126970_b31) 2005
Hannel (10.1016/j.optcom.2021.126970_b7) 2018; 26
Luo (10.1016/j.optcom.2021.126970_b23) 2019; 27
Wu (10.1016/j.optcom.2021.126970_b30) 2020
Chollet (10.1016/j.optcom.2021.126970_b39) 2015
References_xml – reference: L.-C. Chen, Y. Zhu, G. Papandreou, F. Schroff, H. Adam, Encoder–decoder with atrous separable convolution for semantic image segmentation, in: Proceedings of the European Conference on Computer Vision (ECCV) 2018, 801–818.
– volume: 28
  start-page: 2987
  year: 2020
  end-page: 2999
  ident: b4
  article-title: Machine learning holography for 3D particle field imaging
  publication-title: Opt. Express
– volume: 58
  start-page: A202
  year: 2019
  end-page: A208
  ident: b16
  article-title: Focus prediction in digital holographic microscopy using deep convolutional neural networks
  publication-title: Appl. Opt.
– year: 2017
  ident: b33
  article-title: Searching for activation functions
– volume: 7
  start-page: 17141
  year: 2018
  ident: b13
  article-title: Phase recovery and holographic image reconstruction using deep learning in neural networks
  publication-title: Light: Sci. Appl.
– year: 2019
  ident: b10
  article-title: Object detection in 20 years: A survey
– volume: 28
  start-page: 4876
  year: 2020
  end-page: 4887
  ident: b20
  article-title: Redcap: residual encoder–decoder capsule network for holographic image reconstruction
  publication-title: Opt. Express
– volume: 44
  start-page: 4765
  year: 2019
  end-page: 4768
  ident: b14
  article-title: Y-net: a one-to-two deep learning framework for digital holographic reconstruction
  publication-title: Opt. Lett.
– volume: 13
  start-page: 600
  year: 2004
  end-page: 612
  ident: b41
  article-title: Image quality assessment: from error visibility to structural similarity
  publication-title: IEEE Trans. Image Process.
– volume: 23
  start-page: 25440
  year: 2015
  end-page: 25449
  ident: b27
  article-title: Accurate calculation of computer-generated holograms using angular-spectrum layer-oriented method
  publication-title: Opt. Express
– reference: P. Isola, J.-Y. Zhu, T. Zhou, A.A. Efros, Image-to-image translation with conditional adversarial networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2017, pp. 1125–1134.
– volume: 11
  start-page: 4491
  year: 2020
  end-page: 4508
  ident: b15
  article-title: Deep learning-based cell identification and disease diagnosis using spatio-temporal cellular dynamics in compact digital holographic microscopy
  publication-title: Biomed. Opt. Express
– volume: 25
  start-page: 15043
  year: 2017
  end-page: 15057
  ident: b18
  article-title: Automatic phase aberration compensation for digital holographic microscopy based on deep learning background detection
  publication-title: Opt. Express
– volume: 9
  start-page: 1
  year: 2019
  end-page: 13
  ident: b36
  article-title: Deep learning-based super-resolution in coherent imaging systems
  publication-title: Sci. Rep.
– volume: 9
  start-page: 1
  year: 2020
  end-page: 11
  ident: b3
  article-title: An ultra-compact particle size analyser using a CMOS image sensor and machine learning
  publication-title: Light: Sci. Appl.
– year: 2016
  ident: b32
  article-title: Deep Learning
– volume: 10
  start-page: 1
  year: 2020
  end-page: 12
  ident: b22
  article-title: Deep learning-based hologram generation using a white light source
  publication-title: Sci. Rep.
– year: 2020
  ident: b30
  article-title: Dense-U-net with pooling size is 2 and up-sampling size is 2, GitHub repository
– volume: 58
  start-page: G332
  year: 2019
  end-page: G344
  ident: b2
  article-title: Accurate detection of small particles in digital holography using fully convolutional networks
  publication-title: Appl. Opt.
– volume: 58
  start-page: 1900
  year: 2019
  end-page: 1906
  ident: b5
  article-title: Digital holographic particle volume reconstruction using a deep neural network
  publication-title: Appl. Opt.
– year: 2005
  ident: b31
  article-title: Introduction to Fourier Optics
– reference: V.Q.E. Group, Final report from the video quality experts group on the validation of objective models of video quality assessment, VQEG meeting, Ottawa, Canada, March, 2000.
– volume: 27
  start-page: 13581
  year: 2019
  end-page: 13595
  ident: b23
  article-title: Pixel super-resolution for lens-free holographic microscopy using deep learning neural networks
  publication-title: Opt. Express
– volume: 5
  start-page: 704
  year: 2018
  end-page: 710
  ident: b12
  article-title: Extended depth-of-field in holographic imaging using deep-learning-based autofocusing and phase recovery
  publication-title: Optica
– year: 2017
  ident: b34
  article-title: The 2017 davis challenge on video object segmentation
– volume: 26
  start-page: 15221
  year: 2018
  end-page: 15231
  ident: b7
  article-title: Machine-learning techniques for fast and accurate feature localization in holograms of colloidal particles
  publication-title: Opt. Express
– volume: 27
  start-page: 18069
  year: 2019
  end-page: 18084
  ident: b6
  article-title: Regularized inverse holographic volume reconstruction for 3D particle tracking
  publication-title: Opt. Express
– volume: 115
  start-page: 238
  year: 2019
  end-page: 242
  ident: b19
  article-title: Phase aberration compensation for digital holographic microscopy based on double fitting and background segmentation
  publication-title: Opt. Lasers Eng.
– reference: G. Huang, Z. Liu, L.V.D. Maaten, K.Q. Weinberger, densely connected convolutional networks, in: Proceedings of the IEEE conference on computer vision and pattern recognition 2017, pp. 4700–4708.
– volume: 437
  start-page: 337
  year: 2019
  end-page: 341
  ident: b24
  article-title: Compressive holography with resolution improvement and lensless adjustable magnification
  publication-title: Opt. Commun.
– year: 2014
  ident: b40
  article-title: Adam: A method for stochastic optimization
– year: 2019
  ident: b8
  article-title: Computer Holography: Acceleration Algorithms and Hardware Implementations
– year: 2015
  ident: b28
  article-title: Batch normalization: Accelerating deep network training by reducing internal covariate shift
– volume: 45
  start-page: 4220
  year: 2020
  end-page: 4223
  ident: b21
  article-title: Y4-Net: a deep learning solution to one-shot dual-wavelength digital holographic reconstruction
  publication-title: Opt. Lett.
– reference: K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2016, pp. 770–778.
– volume: 52
  start-page: 1
  year: 2019
  end-page: 35
  ident: b9
  article-title: Understanding deep learning techniques for image segmentation
  publication-title: ACM Comput. Surv.
– volume: 6
  start-page: 921
  year: 2019
  end-page: 943
  ident: b11
  article-title: On the use of deep learning for computational imaging
  publication-title: Optica
– year: 2015
  ident: b39
  article-title: Keras, GitHub, GitHub repository
– volume: 7
  start-page: 59037
  year: 2019
  end-page: 59047
  ident: b35
  article-title: Attention dense-u-net for automatic breast mass segmentation in digital mammogram
  publication-title: IEEE Access
– volume: 8
  start-page: 4466
  year: 2017
  end-page: 4479
  ident: b1
  article-title: Automated red blood cells extraction from holographic images using fully convolutional neural networks
  publication-title: Biomed. Opt. Express
– volume: 10
  start-page: 4276
  year: 2019
  end-page: 4289
  ident: b17
  article-title: No-search focus prediction at the single cell level in digital holographic imaging with deep convolutional neural network
  publication-title: Biomed. Opt. Express
– start-page: 234
  year: 2015
  end-page: 241
  ident: b25
  article-title: U-net: Convolutional networks for biomedical image segmentation
  publication-title: International Conference on Medical Image Computing and Computer-Assisted Intervention
– volume: 27
  start-page: 13581
  year: 2019
  ident: 10.1016/j.optcom.2021.126970_b23
  article-title: Pixel super-resolution for lens-free holographic microscopy using deep learning neural networks
  publication-title: Opt. Express
  doi: 10.1364/OE.27.013581
– year: 2017
  ident: 10.1016/j.optcom.2021.126970_b34
– ident: 10.1016/j.optcom.2021.126970_b26
  doi: 10.1109/CVPR.2017.243
– volume: 44
  start-page: 4765
  year: 2019
  ident: 10.1016/j.optcom.2021.126970_b14
  article-title: Y-net: a one-to-two deep learning framework for digital holographic reconstruction
  publication-title: Opt. Lett.
  doi: 10.1364/OL.44.004765
– ident: 10.1016/j.optcom.2021.126970_b38
  doi: 10.1007/978-3-030-01234-2_49
– volume: 115
  start-page: 238
  year: 2019
  ident: 10.1016/j.optcom.2021.126970_b19
  article-title: Phase aberration compensation for digital holographic microscopy based on double fitting and background segmentation
  publication-title: Opt. Lasers Eng.
  doi: 10.1016/j.optlaseng.2018.12.001
– volume: 10
  start-page: 4276
  year: 2019
  ident: 10.1016/j.optcom.2021.126970_b17
  article-title: No-search focus prediction at the single cell level in digital holographic imaging with deep convolutional neural network
  publication-title: Biomed. Opt. Express
  doi: 10.1364/BOE.10.004276
– year: 2005
  ident: 10.1016/j.optcom.2021.126970_b31
– ident: 10.1016/j.optcom.2021.126970_b37
  doi: 10.1109/CVPR.2017.632
– volume: 10
  start-page: 1
  year: 2020
  ident: 10.1016/j.optcom.2021.126970_b22
  article-title: Deep learning-based hologram generation using a white light source
  publication-title: Sci. Rep.
  doi: 10.1038/s41598-020-65716-4
– volume: 5
  start-page: 704
  year: 2018
  ident: 10.1016/j.optcom.2021.126970_b12
  article-title: Extended depth-of-field in holographic imaging using deep-learning-based autofocusing and phase recovery
  publication-title: Optica
  doi: 10.1364/OPTICA.5.000704
– volume: 27
  start-page: 18069
  year: 2019
  ident: 10.1016/j.optcom.2021.126970_b6
  article-title: Regularized inverse holographic volume reconstruction for 3D particle tracking
  publication-title: Opt. Express
  doi: 10.1364/OE.27.018069
– year: 2019
  ident: 10.1016/j.optcom.2021.126970_b8
– volume: 6
  start-page: 921
  year: 2019
  ident: 10.1016/j.optcom.2021.126970_b11
  article-title: On the use of deep learning for computational imaging
  publication-title: Optica
  doi: 10.1364/OPTICA.6.000921
– start-page: 234
  year: 2015
  ident: 10.1016/j.optcom.2021.126970_b25
  article-title: U-net: Convolutional networks for biomedical image segmentation
– year: 2015
  ident: 10.1016/j.optcom.2021.126970_b39
– volume: 8
  start-page: 4466
  year: 2017
  ident: 10.1016/j.optcom.2021.126970_b1
  article-title: Automated red blood cells extraction from holographic images using fully convolutional neural networks
  publication-title: Biomed. Opt. Express
  doi: 10.1364/BOE.8.004466
– ident: 10.1016/j.optcom.2021.126970_b29
  doi: 10.1109/CVPR.2016.90
– year: 2020
  ident: 10.1016/j.optcom.2021.126970_b30
– volume: 9
  start-page: 1
  year: 2019
  ident: 10.1016/j.optcom.2021.126970_b36
  article-title: Deep learning-based super-resolution in coherent imaging systems
  publication-title: Sci. Rep.
– volume: 11
  start-page: 4491
  year: 2020
  ident: 10.1016/j.optcom.2021.126970_b15
  article-title: Deep learning-based cell identification and disease diagnosis using spatio-temporal cellular dynamics in compact digital holographic microscopy
  publication-title: Biomed. Opt. Express
  doi: 10.1364/BOE.399020
– volume: 58
  start-page: G332
  year: 2019
  ident: 10.1016/j.optcom.2021.126970_b2
  article-title: Accurate detection of small particles in digital holography using fully convolutional networks
  publication-title: Appl. Opt.
  doi: 10.1364/AO.58.00G332
– volume: 28
  start-page: 2987
  year: 2020
  ident: 10.1016/j.optcom.2021.126970_b4
  article-title: Machine learning holography for 3D particle field imaging
  publication-title: Opt. Express
  doi: 10.1364/OE.379480
– volume: 45
  start-page: 4220
  year: 2020
  ident: 10.1016/j.optcom.2021.126970_b21
  article-title: Y4-Net: a deep learning solution to one-shot dual-wavelength digital holographic reconstruction
  publication-title: Opt. Lett.
  doi: 10.1364/OL.395445
– volume: 28
  start-page: 4876
  year: 2020
  ident: 10.1016/j.optcom.2021.126970_b20
  article-title: Redcap: residual encoder–decoder capsule network for holographic image reconstruction
  publication-title: Opt. Express
  doi: 10.1364/OE.383350
– volume: 26
  start-page: 15221
  year: 2018
  ident: 10.1016/j.optcom.2021.126970_b7
  article-title: Machine-learning techniques for fast and accurate feature localization in holograms of colloidal particles
  publication-title: Opt. Express
  doi: 10.1364/OE.26.015221
– volume: 13
  start-page: 600
  year: 2004
  ident: 10.1016/j.optcom.2021.126970_b41
  article-title: Image quality assessment: from error visibility to structural similarity
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/TIP.2003.819861
– volume: 7
  start-page: 17141
  year: 2018
  ident: 10.1016/j.optcom.2021.126970_b13
  article-title: Phase recovery and holographic image reconstruction using deep learning in neural networks
  publication-title: Light: Sci. Appl.
  doi: 10.1038/lsa.2017.141
– year: 2014
  ident: 10.1016/j.optcom.2021.126970_b40
– volume: 437
  start-page: 337
  year: 2019
  ident: 10.1016/j.optcom.2021.126970_b24
  article-title: Compressive holography with resolution improvement and lensless adjustable magnification
  publication-title: Opt. Commun.
  doi: 10.1016/j.optcom.2018.12.081
– volume: 7
  start-page: 59037
  year: 2019
  ident: 10.1016/j.optcom.2021.126970_b35
  article-title: Attention dense-u-net for automatic breast mass segmentation in digital mammogram
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2019.2914873
– volume: 25
  start-page: 15043
  year: 2017
  ident: 10.1016/j.optcom.2021.126970_b18
  article-title: Automatic phase aberration compensation for digital holographic microscopy based on deep learning background detection
  publication-title: Opt. Express
  doi: 10.1364/OE.25.015043
– year: 2016
  ident: 10.1016/j.optcom.2021.126970_b32
– volume: 58
  start-page: A202
  year: 2019
  ident: 10.1016/j.optcom.2021.126970_b16
  article-title: Focus prediction in digital holographic microscopy using deep convolutional neural networks
  publication-title: Appl. Opt.
  doi: 10.1364/AO.58.00A202
– volume: 52
  start-page: 1
  year: 2019
  ident: 10.1016/j.optcom.2021.126970_b9
  article-title: Understanding deep learning techniques for image segmentation
  publication-title: ACM Comput. Surv.
  doi: 10.1145/3329784
– volume: 58
  start-page: 1900
  year: 2019
  ident: 10.1016/j.optcom.2021.126970_b5
  article-title: Digital holographic particle volume reconstruction using a deep neural network
  publication-title: Appl. Opt.
  doi: 10.1364/AO.58.001900
– volume: 23
  start-page: 25440
  year: 2015
  ident: 10.1016/j.optcom.2021.126970_b27
  article-title: Accurate calculation of computer-generated holograms using angular-spectrum layer-oriented method
  publication-title: Opt. Express
  doi: 10.1364/OE.23.025440
– year: 2015
  ident: 10.1016/j.optcom.2021.126970_b28
– ident: 10.1016/j.optcom.2021.126970_b42
– volume: 9
  start-page: 1
  year: 2020
  ident: 10.1016/j.optcom.2021.126970_b3
  article-title: An ultra-compact particle size analyser using a CMOS image sensor and machine learning
  publication-title: Light: Sci. Appl.
  doi: 10.1038/s41377-020-0255-6
– year: 2017
  ident: 10.1016/j.optcom.2021.126970_b33
– year: 2019
  ident: 10.1016/j.optcom.2021.126970_b10
SSID ssj0001438
Score 2.5720458
Snippet Digital holographic imaging is able to reconstruct phase and three-dimensional (3D) information of an object from a one-shot two-dimensional (2D) lensless...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 126970
SubjectTerms Deep learning
Dense-U-net
Digital holography
Image reconstruction
Title Dense-U-net: Dense encoder–decoder network for holographic imaging of 3D particle fields
URI https://dx.doi.org/10.1016/j.optcom.2021.126970
Volume 493
WOSCitedRecordID wos000653031900010&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  customDbUrl:
  eissn: 1873-0310
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001438
  issn: 0030-4018
  databaseCode: AIEXJ
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9QwELZgCxIXxFOUl3zgFrkicbJ2uFXdIlihgtQWVlwix7HVVJBE3V1UceI_8A_5JYw9ThqxiJfExVp77fXK82kyMxl_Q8iTFERplNVMiyxlqc5jVmZWMQnCjqvMJMYXg3n7ShwcyMUifxNeFyx9OQHRNPL8PO_-q6hhDITtrs7-hbiHH4UB-AxChxbEDu0fCX4Gjqlhx6wxPurnu5Gjq3RUISG1gVfG96MGs8B9suFJz19d66j-GKoX2YjPoi5sE_l8t-XYoH3deZ5nPb5nMpjp79Zew6-tCc_HYWxeOyLpAZhzZDI4dNHrzyftxew91WLkAL7Qqh7HKBIfdMVbmhg427g8g8qYPwX3Nahfg_pXCs4cW-lYQadYQ3FD2WPc4XSn7VYu88dtvBMn0xwrkfxAo33oXwLDbokjnQXAXCZbichyOSFbuy_3F_Ph-e0KwiOZJ_69_sKlzwrc3OvnBs3ISDm6Qa4H74LuorhukkumuUWu-ixfvbxN3o-w8Yz6Dg3I-Pbla8AEDZiggAk6wgQNmKCtpXxGe0xQxMQdcvx8_2jvBQvFNZgGL3HFhM60EKrUVhqwe2VmpJY25irXMk4V-M1axAasN16qVKiEV2C6VklpbeZsPMnvkknTNuYeoVNlhSkVTLIqnUJjk0pnSZmnlQETrNomvD-hQgfmeVcA5UPRpxieFniuhTvXAs91m7BhVYfMK7-ZL_rDL4L1iFZhAXj55cr7_7zyAbl2AfeHZLI6W5tH5Ir-tKqXZ48DsL4DZhKWgA
linkProvider Elsevier
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Dense-U-net%3A+Dense+encoder%E2%80%93decoder+network+for+holographic+imaging+of+3D+particle+fields&rft.jtitle=Optics+communications&rft.au=Wu%2C+Yufeng&rft.au=Wu%2C+Jiachen&rft.au=Jin%2C+Shangzhong&rft.au=Cao%2C+Liangcai&rft.date=2021-08-15&rft.pub=Elsevier+B.V&rft.issn=0030-4018&rft.eissn=1873-0310&rft.volume=493&rft_id=info:doi/10.1016%2Fj.optcom.2021.126970&rft.externalDocID=S0030401821002200
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0030-4018&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0030-4018&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0030-4018&client=summon