Development of a deep learning-based image processing technique for bubble pattern recognition and shape reconstruction in dense bubbly flows

•Novel CNN-based bubble identification algorithm.•Bubbles detection in images with high bubble overlapping.•Accurate determination of bubbles velocities and size distributions.•High potential for the application to bubbly flows with high gas volume fractions. This work presents a Convolutional Neura...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Chemical engineering science Jg. 230; S. 116163
Hauptverfasser: Cerqueira, Rafael F.L., Paladino, Emilio E.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Ltd 02.02.2021
Schlagworte:
ISSN:0009-2509, 1873-4405
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract •Novel CNN-based bubble identification algorithm.•Bubbles detection in images with high bubble overlapping.•Accurate determination of bubbles velocities and size distributions.•High potential for the application to bubbly flows with high gas volume fractions. This work presents a Convolutional Neural Network (CNN) based method for the shape reconstruction of bubbles in bubbly flows using high-speed camera images. The bubble identification and shape reconstruction adopted a methodology based on a set of anchor points and boxes, where a single anchor point is used for different anchor boxes with various sizes. These anchor points are determined, based on the internal features of the bubble images, which are more easily identifiable, in particular, in regions of the images with high bubble overlapping. This makes possible the application of the procedure to high void fraction bubbly flows. For a given anchor point, different ellipsoidal shapes are suggested as bubble shape candidates and are then correctly chosen by a trained CNN. The CNN training used labeled images from air–water system data set and a hyper-parameter analysis was performed to find the best configuration of the CNN architecture. From this optimal CNN architecture, different high-speed camera acquisitions of bubbly flows were analyzed by the CNN-based bubble shape reconstruction method. In order to gain a better comprehension of the method, experiments were conducted in two gas–liquid systems, air–water and air-aqueous glycerol solution, which resulted in different image parameters, such as brightness, contrast and edge definition. The CNN method trained only with air–water data, showed excellent performance in the cases with air-aqueous glycerol, demonstrating its generalization capability. In addition, the results showed that the deep learning method used in this work is able to detect most of the bubbles present in the high-speed camera images, even in dense bubbly flow configurations. The method developed in this work can be used to further analyze bubbly flows and generate experimental data for the implementation and validation of CFD models.
AbstractList •Novel CNN-based bubble identification algorithm.•Bubbles detection in images with high bubble overlapping.•Accurate determination of bubbles velocities and size distributions.•High potential for the application to bubbly flows with high gas volume fractions. This work presents a Convolutional Neural Network (CNN) based method for the shape reconstruction of bubbles in bubbly flows using high-speed camera images. The bubble identification and shape reconstruction adopted a methodology based on a set of anchor points and boxes, where a single anchor point is used for different anchor boxes with various sizes. These anchor points are determined, based on the internal features of the bubble images, which are more easily identifiable, in particular, in regions of the images with high bubble overlapping. This makes possible the application of the procedure to high void fraction bubbly flows. For a given anchor point, different ellipsoidal shapes are suggested as bubble shape candidates and are then correctly chosen by a trained CNN. The CNN training used labeled images from air–water system data set and a hyper-parameter analysis was performed to find the best configuration of the CNN architecture. From this optimal CNN architecture, different high-speed camera acquisitions of bubbly flows were analyzed by the CNN-based bubble shape reconstruction method. In order to gain a better comprehension of the method, experiments were conducted in two gas–liquid systems, air–water and air-aqueous glycerol solution, which resulted in different image parameters, such as brightness, contrast and edge definition. The CNN method trained only with air–water data, showed excellent performance in the cases with air-aqueous glycerol, demonstrating its generalization capability. In addition, the results showed that the deep learning method used in this work is able to detect most of the bubbles present in the high-speed camera images, even in dense bubbly flow configurations. The method developed in this work can be used to further analyze bubbly flows and generate experimental data for the implementation and validation of CFD models.
ArticleNumber 116163
Author Cerqueira, Rafael F.L.
Paladino, Emilio E.
Author_xml – sequence: 1
  givenname: Rafael F.L.
  surname: Cerqueira
  fullname: Cerqueira, Rafael F.L.
  email: rafaelfc@sinmec.ufsc.br
– sequence: 2
  givenname: Emilio E.
  surname: Paladino
  fullname: Paladino, Emilio E.
  email: paladino@sinmec.ufsc.br
BookMark eNp9kEtOAzEQRC0UJJLAAdj5AhP8mU9GrFD4SpHYwNqyPe3E0cQebCcoh-DOOIQVC1atrtbrUtUEjZx3gNA1JTNKaH2zmWmIM0ZY3mlNa36GxnTe8KIsSTVCY0JIW7CKtBdoEuMmr01DyRh93cMeej9swSXsDZa4AxhwDzI461aFkhE6bLdyBXgIPpvELOMEeu3sxw6w8QGrnVJ9vsuUIDgcQPuVs8l6h6XrcFzLAX5UF1PY6Z-DddnJRTjBB2x6_xkv0bmRfYSr3zlF748Pb4vnYvn69LK4WxaatU0qFBBJTWskZ7SsdVkrbngHFbBS6ZZQmJdNyXVJWMW00YooJkEZyTgxXcUrPkX09FcHH2MAI4aQM4aDoEQc-xQbkaOKY5_i1Gdmmj-Mtkkes6Qgbf8veXsiIUfaWwgiagtOQ2dzKUl03v5DfwPZL5Xn
CitedBy_id crossref_primary_10_1038_s41524_024_01223_8
crossref_primary_10_3390_e23111476
crossref_primary_10_1016_j_ijmultiphaseflow_2025_105246
crossref_primary_10_1016_j_ces_2025_122472
crossref_primary_10_1016_j_ijmultiphaseflow_2024_104952
crossref_primary_10_21603_2074_9414_2023_3_2448
crossref_primary_10_1016_j_measurement_2024_114826
crossref_primary_10_1016_j_pnucene_2024_105108
crossref_primary_10_1016_j_seppur_2024_130300
crossref_primary_10_1016_j_ces_2022_118059
crossref_primary_10_1016_j_expthermflusci_2022_110804
crossref_primary_10_1016_j_ces_2021_116819
crossref_primary_10_3390_mi12111402
crossref_primary_10_3390_mi13010041
crossref_primary_10_1016_j_cjche_2024_12_018
crossref_primary_10_1021_acs_iecr_4c03245
crossref_primary_10_1016_j_ijmultiphaseflow_2022_104169
crossref_primary_10_1016_j_seppur_2024_130979
crossref_primary_10_1016_j_ijmultiphaseflow_2022_104247
crossref_primary_10_3390_w13172318
crossref_primary_10_2478_amns_2023_2_01039
crossref_primary_10_1016_j_cej_2022_135554
crossref_primary_10_1016_j_flowmeasinst_2023_102471
crossref_primary_10_7717_peerj_cs_798
crossref_primary_10_1016_j_ijthermalsci_2024_109447
crossref_primary_10_1088_1361_6501_acb2e1
crossref_primary_10_1016_j_powtec_2024_119464
crossref_primary_10_1016_j_ces_2022_117613
crossref_primary_10_1016_j_cej_2022_137859
crossref_primary_10_1016_j_apt_2025_104862
crossref_primary_10_1016_j_compchemeng_2022_107904
crossref_primary_10_1016_j_oceaneng_2023_113782
crossref_primary_10_1016_j_ijmultiphaseflow_2022_104337
crossref_primary_10_1016_j_compfluid_2024_106396
crossref_primary_10_1016_j_ijmultiphaseflow_2024_104979
crossref_primary_10_1016_j_ijmultiphaseflow_2021_103673
crossref_primary_10_1038_s41598_021_88334_0
crossref_primary_10_1016_j_cej_2021_132138
crossref_primary_10_1016_j_measurement_2025_117321
crossref_primary_10_1016_j_cherd_2024_08_005
crossref_primary_10_3390_hydrogen4030036
crossref_primary_10_3390_s23146582
crossref_primary_10_1080_00223131_2024_2348023
crossref_primary_10_1063_5_0276508
crossref_primary_10_1016_j_matre_2025_100356
crossref_primary_10_1002_aic_18570
crossref_primary_10_1016_j_cej_2023_142763
crossref_primary_10_1016_j_physa_2024_129602
crossref_primary_10_1016_j_ijmultiphaseflow_2022_104149
crossref_primary_10_1016_j_ijmultiphaseflow_2022_104302
crossref_primary_10_1016_j_flowmeasinst_2025_102892
crossref_primary_10_1016_j_ces_2021_116886
crossref_primary_10_1002_ceat_202400009
Cites_doi 10.1016/j.expthermflusci.2018.12.008
10.1016/j.minpro.2010.02.001
10.1016/j.ces.2006.10.012
10.3390/en12142735
10.1016/j.ijmultiphaseflow.2016.04.011
10.1016/j.patrec.2012.03.027
10.1007/s00348-009-0797-0
10.1016/j.flowmeasinst.2009.12.003
10.1016/S0017-9310(00)00046-6
10.1016/j.ces.2019.115467
10.1017/S0022112000002743
10.1016/S0894-1777(02)00198-X
10.1088/0957-0233/18/8/028
10.1016/j.ces.2013.02.043
10.1016/j.ijmultiphaseflow.2019.103194
10.1016/j.ces.2016.02.043
10.1016/j.ces.2014.09.036
10.1088/0957-0233/16/9/007
10.1145/2647868.2654889
10.1109/TSMC.1979.4310076
10.1016/S0009-2509(01)00191-9
10.1016/j.ces.2018.05.029
10.1016/S0167-8655(99)00130-0
ContentType Journal Article
Copyright 2020 Elsevier Ltd
Copyright_xml – notice: 2020 Elsevier Ltd
DBID AAYXX
CITATION
DOI 10.1016/j.ces.2020.116163
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1873-4405
ExternalDocumentID 10_1016_j_ces_2020_116163
S0009250920306953
GroupedDBID --K
--M
-~X
.~1
0R~
1B1
1~.
1~5
29B
4.4
457
4G.
5GY
5VS
6J9
7-5
71M
8P~
9JN
AABNK
AACTN
AAEDT
AAEDW
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAXUO
ABFNM
ABFRF
ABJNI
ABMAC
ABNUV
ABYKQ
ACBEA
ACDAQ
ACGFO
ACGFS
ACNCT
ACRLP
ADBBV
ADEWK
ADEZE
AEBSH
AEFWE
AEKER
AENEX
AFKWA
AFTJW
AGHFR
AGUBO
AGYEJ
AHHHB
AHPOS
AIEXJ
AIKHN
AITUG
AJOXV
AKURH
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AXJTR
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EFLBG
ENUVR
EO8
EO9
EP2
EP3
F5P
FDB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
HLY
IHE
J1W
KOM
LX7
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
RNS
ROL
RPZ
SCE
SDF
SDG
SDP
SES
SPC
SPCBC
SSG
SSZ
T5K
XPP
ZMT
~02
~G-
9DU
AAQXK
AATTM
AAXKI
AAYWO
AAYXX
ABDPE
ABWVN
ABXDB
ACLOT
ACRPL
ACVFH
ADCNI
ADMUD
ADNMO
AEIPS
AEUPX
AFJKZ
AFPUW
AGQPQ
AI.
AIDUJ
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
APXCP
ASPBG
AVWKF
AZFZN
BBWZM
CITATION
EFKBS
EJD
FEDTE
FGOYB
HVGLF
HZ~
NDZJH
R2-
SC5
SEW
T9H
VH1
WUQ
Y6R
ZY4
~HD
ID FETCH-LOGICAL-c297t-be0a1f9fa32146c46b3f3de5e24bc901e84743c40252cfcb0b2aebfa230fd5353
ISICitedReferencesCount 68
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000600281200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0009-2509
IngestDate Sat Nov 29 07:31:39 EST 2025
Tue Nov 18 22:22:38 EST 2025
Fri Feb 23 02:46:19 EST 2024
IsPeerReviewed true
IsScholarly true
Keywords Deep learning
Bubbly flow
Convolution neural networks
Bubble size distribution
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c297t-be0a1f9fa32146c46b3f3de5e24bc901e84743c40252cfcb0b2aebfa230fd5353
ParticipantIDs crossref_primary_10_1016_j_ces_2020_116163
crossref_citationtrail_10_1016_j_ces_2020_116163
elsevier_sciencedirect_doi_10_1016_j_ces_2020_116163
PublicationCentury 2000
PublicationDate 2021-02-02
PublicationDateYYYYMMDD 2021-02-02
PublicationDate_xml – month: 02
  year: 2021
  text: 2021-02-02
  day: 02
PublicationDecade 2020
PublicationTitle Chemical engineering science
PublicationYear 2021
Publisher Elsevier Ltd
Publisher_xml – name: Elsevier Ltd
References Cerqueira, Paladino, Brito, Maliska, Meneghini (b0040) 2019; 102
Ren, S., He, K., Girshick, R., Sun, J., 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91–99.
Dhillon, Verma (b0055) 2019
Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., Darrell, T., 2014. Caffe: Convolutional architecture for fast feature embedding. arXiv preprint arXiv:1408.5093.
Fu, Liu (b0060) 2016; 84
Akhmetbekov, Alekseenko, Dulin, Markovich, Pervunin (b0015) 2010; 48
Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., Devin, M., Ghemawat, S., Goodfellow, I., Harp, A., Irving, G., Isard, M., Jia, Y., Jozefowicz, R., Kaiser, L., Kudlur, M., Levenberg, J., Mané, D., Monga, R., Moore, S., Murray, D., Olah, C., Schuster, M., Shlens, J., Steiner, B., Sutskever, I., Talwar, K., Tucker, P., Vanhoucke, V., Vasudevan, V., Viégas, F., Vinyals, O., Warden, P., Wattenberg, M., Wicke, M., Yu, Y., Zheng, X., 2015. TensorFlow: Large-scale machine learning on heterogeneous systems.
Karn, Ellis, Arndt, Hong (b0090) 2015; 122
Paszke, A., Gross, S., Chintala, S., Chanan, G., Yang, E., DeVito, Z., Lin, Z., Desmaison, A., Antiga, L., Lerer, A., 2017. Automatic differentiation in pytorch.
Cerqueira, Paladino, Ynumaru, Maliska (b0035) 2018; 189
Poletaev, Tokarev, Pervunin (b0130) 2020
Rasband, W.S. et al., 1997. Imagej.
Zhang, Jiang, Liu (b0165) 2012; 33
Besagni, Inzoli (b0020) 2016; 146
Da Silva., M.J., Thiele, S., Abdulkareem, L., Azzopardi, B.J., Hampel, U., 2010. High-resolution gas-oil two-phase flow visualization with a capacitance wire-mesh sensor. Flow Measur. Instrument. 21, 191–197. doi:10.1016/j.flowmeasinst.2009.12.003.
Acuña, Finch (b0010) 2010; 94
Kulkarni, Joshi, Kumar, Kulkarni (b0105) 2001; 56
Bröder, Sommerfeld (b0030) 2007; 18
Garnier, Lance, Marié (b0065) 2002; 26
Simonnet, Gentric, Olmos, Midoux (b0150) 2007
Srivastava, Hinton, Krizhevsky, Sutskever, Salakhutdinov (b0155) 2014; 15
software available from tensorflow.org.
Ioffe, S., Szegedy, C., 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167.
Lau, Deen, Kuipers (b0110) 2013; 94
Haas, Schubert, Eickhoff, Pfeifer (b0070) 2020; 216
Lobanov, Pakhomov, Terekhov (b0115) 2019; 12
.
Kingma, D.P., Ba, J., 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
Chollet, F. et al., 2015. Keras.
Zenit, Koch, Sangani (b0160) 2001; 429
Shen, Song, Iguchi, Yamamoto (b0145) 2000; 21
Kim, Fu, Wang, Ishii (b0095) 2000; 43
Honkanen, Saarenrinne, Stoor, Niinimäki (b0075) 2005; 16
Bradski (b0025) 2000
Otsu (b0120) 1979; 20
Garnier (10.1016/j.ces.2020.116163_b0065) 2002; 26
Besagni (10.1016/j.ces.2020.116163_b0020) 2016; 146
10.1016/j.ces.2020.116163_b0045
10.1016/j.ces.2020.116163_b0100
10.1016/j.ces.2020.116163_b0005
Haas (10.1016/j.ces.2020.116163_b0070) 2020; 216
10.1016/j.ces.2020.116163_b0125
10.1016/j.ces.2020.116163_b0080
Bradski (10.1016/j.ces.2020.116163_b0025) 2000
Poletaev (10.1016/j.ces.2020.116163_b0130) 2020
Lobanov (10.1016/j.ces.2020.116163_b0115) 2019; 12
Bröder (10.1016/j.ces.2020.116163_b0030) 2007; 18
10.1016/j.ces.2020.116163_b0085
10.1016/j.ces.2020.116163_b0140
Honkanen (10.1016/j.ces.2020.116163_b0075) 2005; 16
Shen (10.1016/j.ces.2020.116163_b0145) 2000; 21
Lau (10.1016/j.ces.2020.116163_b0110) 2013; 94
Kim (10.1016/j.ces.2020.116163_b0095) 2000; 43
Dhillon (10.1016/j.ces.2020.116163_b0055) 2019
Acuña (10.1016/j.ces.2020.116163_b0010) 2010; 94
Zhang (10.1016/j.ces.2020.116163_b0165) 2012; 33
Zenit (10.1016/j.ces.2020.116163_b0160) 2001; 429
Simonnet (10.1016/j.ces.2020.116163_b0150) 2007
Srivastava (10.1016/j.ces.2020.116163_b0155) 2014; 15
Cerqueira (10.1016/j.ces.2020.116163_b0035) 2018; 189
10.1016/j.ces.2020.116163_b0135
Kulkarni (10.1016/j.ces.2020.116163_b0105) 2001; 56
10.1016/j.ces.2020.116163_b0050
Otsu (10.1016/j.ces.2020.116163_b0120) 1979; 20
Akhmetbekov (10.1016/j.ces.2020.116163_b0015) 2010; 48
Cerqueira (10.1016/j.ces.2020.116163_b0040) 2019; 102
Fu (10.1016/j.ces.2020.116163_b0060) 2016; 84
Karn (10.1016/j.ces.2020.116163_b0090) 2015; 122
References_xml – volume: 146
  start-page: 259
  year: 2016
  end-page: 290
  ident: b0020
  article-title: Comprehensive experimental investigation of counter-current bubble column hydrodynamics: Holdup, flow regime transition, bubble size distributions and local flow properties
  publication-title: Chem. Eng. Sci.
– volume: 21
  start-page: 21
  year: 2000
  end-page: 30
  ident: b0145
  article-title: A method for recognizing particles in overlapped particle images
  publication-title: Pattern Recogn. Lett.
– start-page: 103194
  year: 2020
  ident: b0130
  article-title: Bubble recognition using neural networks: application to the analysis of a two-phase bubbly jet
  publication-title: Int. J. Multiph. Flow
– year: 2019
  ident: b0055
  article-title: Convolutional neural network: a review of models, methodologies and applications to object detection
  publication-title: Progress Artif. Intell.
– volume: 16
  start-page: 1760
  year: 2005
  end-page: 1770
  ident: b0075
  article-title: Recognition of highly overlapping ellipse-like bubble images
  publication-title: Meas. Sci. Technol. Meas. Sci. Technol
– reference: Chollet, F. et al., 2015. Keras.
– reference: Da Silva., M.J., Thiele, S., Abdulkareem, L., Azzopardi, B.J., Hampel, U., 2010. High-resolution gas-oil two-phase flow visualization with a capacitance wire-mesh sensor. Flow Measur. Instrument. 21, 191–197. doi:10.1016/j.flowmeasinst.2009.12.003.
– reference: Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., Darrell, T., 2014. Caffe: Convolutional architecture for fast feature embedding. arXiv preprint arXiv:1408.5093.
– volume: 94
  start-page: 20
  year: 2013
  end-page: 29
  ident: b0110
  article-title: Development of an image measurement technique for size distribution in dense bubbly flows
  publication-title: Chem. Eng. Sci.
– volume: 48
  start-page: 615
  year: 2010
  end-page: 629
  ident: b0015
  article-title: Planar fluorescence for round bubble imaging and its application for the study of an axisymmetric two-phase jet
  publication-title: Exp. Fluids
– reference: Rasband, W.S. et al., 1997. Imagej.
– reference: Ioffe, S., Szegedy, C., 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167.
– volume: 102
  start-page: 421
  year: 2019
  end-page: 451
  ident: b0040
  article-title: Experimental apparatus and flow instrumentation for the investigation of a quasi-real slug flows in vertical ducts
  publication-title: Exp. Thermal Fluid Sci.
– volume: 122
  start-page: 240
  year: 2015
  end-page: 249
  ident: b0090
  article-title: An integrative image measurement technique for dense bubbly flows with a wide size distribution
  publication-title: Chem. Eng. Sci.
– year: 2000
  ident: b0025
  article-title: The OpenCV Library
  publication-title: Dr. Dobb’s J. Softw. Tools.
– volume: 216
  start-page: 115467
  year: 2020
  ident: b0070
  article-title: BubCNN: Bubble detection using Faster RCNN and shape regression network
  publication-title: Chem. Eng. Sci.
– reference: Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., Devin, M., Ghemawat, S., Goodfellow, I., Harp, A., Irving, G., Isard, M., Jia, Y., Jozefowicz, R., Kaiser, L., Kudlur, M., Levenberg, J., Mané, D., Monga, R., Moore, S., Murray, D., Olah, C., Schuster, M., Shlens, J., Steiner, B., Sutskever, I., Talwar, K., Tucker, P., Vanhoucke, V., Vasudevan, V., Viégas, F., Vinyals, O., Warden, P., Wattenberg, M., Wicke, M., Yu, Y., Zheng, X., 2015. TensorFlow: Large-scale machine learning on heterogeneous systems.
– volume: 189
  start-page: 1
  year: 2018
  end-page: 23
  ident: b0035
  article-title: Image processing techniques for the measurement of two-phase bubbly pipe flows using particle image and tracking velocimetry (PIV/PTV)
  publication-title: Chem. Eng. Sci.
– volume: 84
  start-page: 217
  year: 2016
  end-page: 228
  ident: b0060
  article-title: Development of a robust image processing technique for bubbly flow measurement in a narrow rectangular channel
  publication-title: Int. J. Multiph. Flow
– volume: 33
  start-page: 1543
  year: 2012
  end-page: 1548
  ident: b0165
  article-title: A method for recognizing overlapping elliptical bubbles in bubble image
  publication-title: Pattern Recogn. Lett.
– reference: software available from tensorflow.org.
– volume: 43
  start-page: 4101
  year: 2000
  end-page: 4118
  ident: b0095
  article-title: Development of the miniaturized four-sensor conductivity probe and the signal processing scheme
  publication-title: Int. J. Heat Mass Transf.
– volume: 12
  year: 2019
  ident: b0115
  article-title: Experimental and numerical study of the flow and heat transfer in a bubbly turbulent flow in a pipe with sudden expansion
  publication-title: Energies
– volume: 429
  start-page: 307
  year: 2001
  end-page: 342
  ident: b0160
  article-title: Measurements of the average properties of a suspension of bubbles rising in a vertical channel
  publication-title: J. Fluid Mech.
– reference: Ren, S., He, K., Girshick, R., Sun, J., 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91–99.
– volume: 94
  start-page: 147
  year: 2010
  end-page: 158
  ident: b0010
  article-title: Tracking velocity of multiple bubbles in a swarm
  publication-title: Int. J. Miner. Process.
– volume: 18
  start-page: 2513
  year: 2007
  end-page: 2528
  ident: b0030
  article-title: Planar shadow image velocimetry for the analysis of the hydrodynamics in bubbly flows
  publication-title: Meas. Sci. Technol.
– volume: 15
  start-page: 1929
  year: 2014
  end-page: 1958
  ident: b0155
  article-title: Dropout: a simple way to prevent neural networks from overfitting
  publication-title: J. Machine Learn. Res.
– reference: .
– reference: Paszke, A., Gross, S., Chintala, S., Chanan, G., Yang, E., DeVito, Z., Lin, Z., Desmaison, A., Antiga, L., Lerer, A., 2017. Automatic differentiation in pytorch.
– reference: Kingma, D.P., Ba, J., 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
– year: 2007
  ident: b0150
  article-title: Experimental determination of the drag coefficient in a swarm of bubbles
  publication-title: Chem. Eng. Sci.
– volume: 26
  start-page: 811
  year: 2002
  end-page: 815
  ident: b0065
  article-title: Measurement of local flow characteristics in buoyancy-driven bubbly flow at high void fraction
  publication-title: Exp. Thermal Fluid Sci.
– volume: 56
  start-page: 5037
  year: 2001
  end-page: 5048
  ident: b0105
  article-title: Application of multiresolution analysis for simultaneous measurement of gas and liquid velocities and fractional gas hold-up in bubble column using LDA
  publication-title: Chem. Eng. Sci.
– volume: 20
  start-page: 62
  year: 1979
  end-page: 66
  ident: b0120
  article-title: A threshold selection method from gray-level histograms
  publication-title: IEEE Trans. Syst. Man Cybernet.
– ident: 10.1016/j.ces.2020.116163_b0135
– ident: 10.1016/j.ces.2020.116163_b0005
– volume: 102
  start-page: 421
  year: 2019
  ident: 10.1016/j.ces.2020.116163_b0040
  article-title: Experimental apparatus and flow instrumentation for the investigation of a quasi-real slug flows in vertical ducts
  publication-title: Exp. Thermal Fluid Sci.
  doi: 10.1016/j.expthermflusci.2018.12.008
– volume: 94
  start-page: 147
  year: 2010
  ident: 10.1016/j.ces.2020.116163_b0010
  article-title: Tracking velocity of multiple bubbles in a swarm
  publication-title: Int. J. Miner. Process.
  doi: 10.1016/j.minpro.2010.02.001
– year: 2007
  ident: 10.1016/j.ces.2020.116163_b0150
  article-title: Experimental determination of the drag coefficient in a swarm of bubbles
  publication-title: Chem. Eng. Sci.
  doi: 10.1016/j.ces.2006.10.012
– volume: 12
  year: 2019
  ident: 10.1016/j.ces.2020.116163_b0115
  article-title: Experimental and numerical study of the flow and heat transfer in a bubbly turbulent flow in a pipe with sudden expansion
  publication-title: Energies
  doi: 10.3390/en12142735
– volume: 84
  start-page: 217
  year: 2016
  ident: 10.1016/j.ces.2020.116163_b0060
  article-title: Development of a robust image processing technique for bubbly flow measurement in a narrow rectangular channel
  publication-title: Int. J. Multiph. Flow
  doi: 10.1016/j.ijmultiphaseflow.2016.04.011
– volume: 33
  start-page: 1543
  year: 2012
  ident: 10.1016/j.ces.2020.116163_b0165
  article-title: A method for recognizing overlapping elliptical bubbles in bubble image
  publication-title: Pattern Recogn. Lett.
  doi: 10.1016/j.patrec.2012.03.027
– volume: 48
  start-page: 615
  year: 2010
  ident: 10.1016/j.ces.2020.116163_b0015
  article-title: Planar fluorescence for round bubble imaging and its application for the study of an axisymmetric two-phase jet
  publication-title: Exp. Fluids
  doi: 10.1007/s00348-009-0797-0
– ident: 10.1016/j.ces.2020.116163_b0050
  doi: 10.1016/j.flowmeasinst.2009.12.003
– volume: 43
  start-page: 4101
  year: 2000
  ident: 10.1016/j.ces.2020.116163_b0095
  article-title: Development of the miniaturized four-sensor conductivity probe and the signal processing scheme
  publication-title: Int. J. Heat Mass Transf.
  doi: 10.1016/S0017-9310(00)00046-6
– volume: 216
  start-page: 115467
  year: 2020
  ident: 10.1016/j.ces.2020.116163_b0070
  article-title: BubCNN: Bubble detection using Faster RCNN and shape regression network
  publication-title: Chem. Eng. Sci.
  doi: 10.1016/j.ces.2019.115467
– ident: 10.1016/j.ces.2020.116163_b0080
– volume: 429
  start-page: 307
  year: 2001
  ident: 10.1016/j.ces.2020.116163_b0160
  article-title: Measurements of the average properties of a suspension of bubbles rising in a vertical channel
  publication-title: J. Fluid Mech.
  doi: 10.1017/S0022112000002743
– volume: 26
  start-page: 811
  year: 2002
  ident: 10.1016/j.ces.2020.116163_b0065
  article-title: Measurement of local flow characteristics in buoyancy-driven bubbly flow at high void fraction
  publication-title: Exp. Thermal Fluid Sci.
  doi: 10.1016/S0894-1777(02)00198-X
– volume: 18
  start-page: 2513
  year: 2007
  ident: 10.1016/j.ces.2020.116163_b0030
  article-title: Planar shadow image velocimetry for the analysis of the hydrodynamics in bubbly flows
  publication-title: Meas. Sci. Technol.
  doi: 10.1088/0957-0233/18/8/028
– volume: 94
  start-page: 20
  year: 2013
  ident: 10.1016/j.ces.2020.116163_b0110
  article-title: Development of an image measurement technique for size distribution in dense bubbly flows
  publication-title: Chem. Eng. Sci.
  doi: 10.1016/j.ces.2013.02.043
– ident: 10.1016/j.ces.2020.116163_b0140
– year: 2000
  ident: 10.1016/j.ces.2020.116163_b0025
  article-title: The OpenCV Library
  publication-title: Dr. Dobb’s J. Softw. Tools.
– volume: 15
  start-page: 1929
  year: 2014
  ident: 10.1016/j.ces.2020.116163_b0155
  article-title: Dropout: a simple way to prevent neural networks from overfitting
  publication-title: J. Machine Learn. Res.
– start-page: 103194
  year: 2020
  ident: 10.1016/j.ces.2020.116163_b0130
  article-title: Bubble recognition using neural networks: application to the analysis of a two-phase bubbly jet
  publication-title: Int. J. Multiph. Flow
  doi: 10.1016/j.ijmultiphaseflow.2019.103194
– volume: 146
  start-page: 259
  year: 2016
  ident: 10.1016/j.ces.2020.116163_b0020
  article-title: Comprehensive experimental investigation of counter-current bubble column hydrodynamics: Holdup, flow regime transition, bubble size distributions and local flow properties
  publication-title: Chem. Eng. Sci.
  doi: 10.1016/j.ces.2016.02.043
– volume: 122
  start-page: 240
  year: 2015
  ident: 10.1016/j.ces.2020.116163_b0090
  article-title: An integrative image measurement technique for dense bubbly flows with a wide size distribution
  publication-title: Chem. Eng. Sci.
  doi: 10.1016/j.ces.2014.09.036
– ident: 10.1016/j.ces.2020.116163_b0100
– volume: 16
  start-page: 1760
  year: 2005
  ident: 10.1016/j.ces.2020.116163_b0075
  article-title: Recognition of highly overlapping ellipse-like bubble images
  publication-title: Meas. Sci. Technol. Meas. Sci. Technol
  doi: 10.1088/0957-0233/16/9/007
– ident: 10.1016/j.ces.2020.116163_b0085
  doi: 10.1145/2647868.2654889
– volume: 20
  start-page: 62
  year: 1979
  ident: 10.1016/j.ces.2020.116163_b0120
  article-title: A threshold selection method from gray-level histograms
  publication-title: IEEE Trans. Syst. Man Cybernet.
  doi: 10.1109/TSMC.1979.4310076
– ident: 10.1016/j.ces.2020.116163_b0125
– year: 2019
  ident: 10.1016/j.ces.2020.116163_b0055
  article-title: Convolutional neural network: a review of models, methodologies and applications to object detection
  publication-title: Progress Artif. Intell.
– volume: 56
  start-page: 5037
  year: 2001
  ident: 10.1016/j.ces.2020.116163_b0105
  article-title: Application of multiresolution analysis for simultaneous measurement of gas and liquid velocities and fractional gas hold-up in bubble column using LDA
  publication-title: Chem. Eng. Sci.
  doi: 10.1016/S0009-2509(01)00191-9
– volume: 189
  start-page: 1
  year: 2018
  ident: 10.1016/j.ces.2020.116163_b0035
  article-title: Image processing techniques for the measurement of two-phase bubbly pipe flows using particle image and tracking velocimetry (PIV/PTV)
  publication-title: Chem. Eng. Sci.
  doi: 10.1016/j.ces.2018.05.029
– volume: 21
  start-page: 21
  year: 2000
  ident: 10.1016/j.ces.2020.116163_b0145
  article-title: A method for recognizing particles in overlapped particle images
  publication-title: Pattern Recogn. Lett.
  doi: 10.1016/S0167-8655(99)00130-0
– ident: 10.1016/j.ces.2020.116163_b0045
SSID ssj0007710
Score 2.5916498
Snippet •Novel CNN-based bubble identification algorithm.•Bubbles detection in images with high bubble overlapping.•Accurate determination of bubbles velocities and...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 116163
SubjectTerms Bubble size distribution
Bubbly flow
Convolution neural networks
Deep learning
Title Development of a deep learning-based image processing technique for bubble pattern recognition and shape reconstruction in dense bubbly flows
URI https://dx.doi.org/10.1016/j.ces.2020.116163
Volume 230
WOSCitedRecordID wos000600281200001&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: 1873-4405
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0007710
  issn: 0009-2509
  databaseCode: AIEXJ
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Jb9QwFLaGKQc4IFa1bPKBE1FGTuxsxwpNBaiqkCjS3CLbsSFVmolmStX-AI78Z56XLMMmQOISjax548jvG_vZ_t73EHohqWCMpyJMNFMhE0SGeaSoOW0iqaQZSZXVmT3OTk7y1ap4N5t96XNhLpusbfOrq6L7r66GNnC2SZ39C3cPPwoN8BmcDk9wOzz_yPETGpBLfqyU6vrqEB9Ds2xVQX1uuDqdyxKwGVODlqvlb34WJqOqs-KbJuHFs4w8dXn7iXfKto76s45W226VM74OdLP2AXsvhNBrE6hRAzHwK_BwFaI28A71xoW0XHPVBEeL48V409UY0r89312e1029DpaL6clFHFmy87jPHVJqRv6Sm6KLEOIyN48qNyvnGQ0ZI8l02o7dfc4PS4A7jThbwPjB9j82i0Ia-Ul0V1n7venLdBWbjVOR0BtoL86SIp-jvcM3y9XbYUnPsoj0JfmMQX89bomC33X08wBnErSc3kV3_G4DHzqU3EMz1d5HtycalA_Q1wle8Fpjjg1e8C5esMULHvGCB7xgwAt2eMEeL3iCFwx4wRYveBcvuG6xxYszvsYWLw_Rh6Pl6avXoa_REcq4yC5CoQiPdKG5KXiVSpYKqmmlEhUzISHWVBD9MCoZhNax1FIQEXMlNAfv6SqhCX2E5u26VfsI5znjgkujV1QxKVJwuk6JiooqUTSn5ACRfmBL6QXsTR2VpuyZimclDEJpfFE6Xxygl4NJ59Rbfvdl1nur9OB3YWUJ0Pq12eN_M3uCbo3_iadoDqOvnqGb8vKi3m6eewB-A2hYrsI
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=Development+of+a+deep+learning-based+image+processing+technique+for+bubble+pattern+recognition+and+shape+reconstruction+in+dense+bubbly+flows&rft.jtitle=Chemical+engineering+science&rft.au=Cerqueira%2C+Rafael+F.L.&rft.au=Paladino%2C+Emilio+E.&rft.date=2021-02-02&rft.pub=Elsevier+Ltd&rft.issn=0009-2509&rft.eissn=1873-4405&rft.volume=230&rft_id=info:doi/10.1016%2Fj.ces.2020.116163&rft.externalDocID=S0009250920306953
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0009-2509&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0009-2509&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0009-2509&client=summon