Image Restoration by Learning Morphological Opening-Closing Network

Mathematical morphology is a powerful tool for image processing tasks. The main difficulty in designing mathematical morphological algorithm is deciding the order of operators/filters and the corresponding structuring elements (SEs). In this work, we develop morphological network composed of alterna...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Mathematical Morphology - Theory and Applications Ročník 4; číslo 1; s. 87 - 107
Hlavní autoři: Mondal, Ranjan, Dey, Moni Shankar, Chanda, Bhabatosh
Médium: Journal Article
Jazyk:angličtina
Vydáno: De Gruyter Open 01.01.2020
Témata:
68T07
68T45
68U10
De-Hazing
De-Raining
Dilation Erosion Neurons
Learning structuring element
Morphological Network
Opening-Closing Network
ISSN:2353-3390, 2353-3390
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Mathematical morphology is a powerful tool for image processing tasks. The main difficulty in designing mathematical morphological algorithm is deciding the order of operators/filters and the corresponding structuring elements (SEs). In this work, we develop morphological network composed of alternate sequences of dilation and erosion layers, which depending on learned SEs, may form opening or closing layers. These layers in the right order along with linear combination (of their outputs) are useful in extracting image features and processing them. Structuring elements in the network are learned by back-propagation method guided by minimization of the loss function. Efficacy of the proposed network is established by applying it to two interesting image restoration problems, namely and . Results are comparable to that of many state-of-the-art algorithms for most of the images. It is also worth mentioning that the number of network parameters to handle is much less than that of popular convolutional neural network for similar tasks. The source code can be found here
AbstractList Mathematical morphology is a powerful tool for image processing tasks. The main difficulty in designing mathematical morphological algorithm is deciding the order of operators/filters and the corresponding structuring elements (SEs). In this work, we develop morphological network composed of alternate sequences of dilation and erosion layers, which depending on learned SEs, may form opening or closing layers. These layers in the right order along with linear combination (of their outputs) are useful in extracting image features and processing them. Structuring elements in the network are learned by back-propagation method guided by minimization of the loss function. Efficacy of the proposed network is established by applying it to two interesting image restoration problems, namely and . Results are comparable to that of many state-of-the-art algorithms for most of the images. It is also worth mentioning that the number of network parameters to handle is much less than that of popular convolutional neural network for similar tasks. The source code can be found here
Mathematical morphology is a powerful tool for image processing tasks. The main difficulty in designing mathematical morphological algorithm is deciding the order of operators/filters and the corresponding structuring elements (SEs). In this work, we develop morphological network composed of alternate sequences of dilation and erosion layers, which depending on learned SEs, may form opening or closing layers. These layers in the right order along with linear combination (of their outputs) are useful in extracting image features and processing them. Structuring elements in the network are learned by back-propagation method guided by minimization of the loss function. Efficacy of the proposed network is established by applying it to two interesting image restoration problems, namely de-raining and de-hazing . Results are comparable to that of many state-of-the-art algorithms for most of the images. It is also worth mentioning that the number of network parameters to handle is much less than that of popular convolutional neural network for similar tasks. The source code can be found here https://github.com/ranjanZ/Mophological-Opening-Closing-Net
Author Mondal, Ranjan
Chanda, Bhabatosh
Dey, Moni Shankar
Author_xml – sequence: 1
  givenname: Ranjan
  surname: Mondal
  fullname: Mondal, Ranjan
  email: ranjan15_r@isical.ac.in
  organization: Indian Statistical Institute,Kolkata, India
– sequence: 2
  givenname: Moni Shankar
  surname: Dey
  fullname: Dey, Moni Shankar
  email: msdey.iitb@gmail.com
  organization: Indian Institute of Technology,Bombay, India
– sequence: 3
  givenname: Bhabatosh
  surname: Chanda
  fullname: Chanda, Bhabatosh
  email: chanda@isical.ac.in
  organization: Indian Statistical Institute,Kolkata, India
BookMark eNp1kE1Lw0AQhhepYK09e80fWLsfySbBkwS1hWhB9LxsNrNpNMmG3ZSSf29iPXjxNC_z8gzDc40Wne0AoVtK7mhEo02rhkOLGWEEE0r4BVoyHnHMeUoWf_IVWntfFyQMBeEpp0uU7VpVQfAGfrBODbXtgmIMclCuq7sqeLGuP9jGVrVWTbDvYd7irLF-bl9hOFn3dYMujWo8rH_nCn08Pb5nW5zvn3fZQ4415TzGCYEwKagRSVhq0MaIkqVaJJowEcUcmDYp0SWLgIrUxFFchEpRKgwD0DpVfIU257vaWe8dGNm7ulVulJTIWYP80SBnDXLWMBH3Z-KkmgFcCZU7jlOQn_bouunX_8iQJjH_BkFuZ6c
Cites_doi 10.1117/12.976517
10.1007/978-3-319-46475-6_10
10.1007/978-3-540-71992-2_87
10.1109/ICCV.2015.169
10.1109/ICCV.2013.82
10.1109/CVPRW.2018.00137
10.1016/S0165-1684(99)00161-9
10.1109/CVPRW.2018.00119
10.1145/2651362
10.1109/CVPR.2016.299
10.1007/978-3-319-46478-7_34
10.1016/j.patcog.2020.107246
10.1109/TPAMI.2010.168
10.1109/CVPRW.2018.00135
10.1109/TIP.2015.2446191
10.1007/978-3-030-14085-4_21
10.1109/TIP.2016.2598681
10.1007/978-3-319-24574-4_28
10.1109/CVPR.2018.00337
10.1109/ICCV.2015.303
10.1007/978-3-662-03039-4_13
10.1109/ICCV.2015.388
10.1109/TIP.2003.819861
10.1109/ICIP.2004.1421765
10.1109/CVPR.2014.383
10.1109/ICDAR.2019.00020
10.1109/TIP.2017.2662206
10.1109/ICIP.2016.7532754
10.1201/9781420027822.ch14
10.1016/0734-189X(86)90004-6
10.1109/TIP.2018.2839891
10.1109/TIP.2017.2691802
10.1109/CVPR.2016.185
10.1109/34.67627
ContentType Journal Article
DBID AAYXX
CITATION
DOI 10.1515/mathm-2020-0103
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
CrossRef
DeliveryMethod fulltext_linktorsrc
EISSN 2353-3390
EndPage 107
ExternalDocumentID 10_1515_mathm_2020_0103
10_1515_mathm_2020_01034187
GroupedDBID AAFWJ
ALMA_UNASSIGNED_HOLDINGS
AAYXX
CITATION
ID FETCH-LOGICAL-c1337-80e48b1f684dcecff6d29c68c026573e2cf90cd25e169f757b4aa116f2eecc9a3
ISSN 2353-3390
IngestDate Sat Nov 29 05:05:14 EST 2025
Sat Sep 06 17:01:20 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 1
Language English
License This work is licensed under the Creative Commons Attribution 4.0 International License.
http://creativecommons.org/licenses/by/4.0
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c1337-80e48b1f684dcecff6d29c68c026573e2cf90cd25e169f757b4aa116f2eecc9a3
OpenAccessLink https://www.degruyter.com/doi/10.1515/mathm-2020-0103
PageCount 21
ParticipantIDs crossref_primary_10_1515_mathm_2020_0103
walterdegruyter_journals_10_1515_mathm_2020_01034187
PublicationCentury 2000
PublicationDate 2020-01-01
PublicationDateYYYYMMDD 2020-01-01
PublicationDate_xml – month: 01
  year: 2020
  text: 2020-01-01
  day: 01
PublicationDecade 2020
PublicationTitle Mathematical Morphology - Theory and Applications
PublicationYear 2020
Publisher De Gruyter Open
Publisher_xml – name: De Gruyter Open
References 2022042712261288296_j_mathm-2020-0103_ref_001_w2aab3b7c10b1b6b1ab1ab1Aa
2022042712261288296_j_mathm-2020-0103_ref_049_w2aab3b7c10b1b6b1ab1ac49Aa
2022042712261288296_j_mathm-2020-0103_ref_018_w2aab3b7c10b1b6b1ab1ac18Aa
2022042712261288296_j_mathm-2020-0103_ref_036_w2aab3b7c10b1b6b1ab1ac36Aa
2022042712261288296_j_mathm-2020-0103_ref_023_w2aab3b7c10b1b6b1ab1ac23Aa
2022042712261288296_j_mathm-2020-0103_ref_041_w2aab3b7c10b1b6b1ab1ac41Aa
2022042712261288296_j_mathm-2020-0103_ref_010_w2aab3b7c10b1b6b1ab1ac10Aa
2022042712261288296_j_mathm-2020-0103_ref_004_w2aab3b7c10b1b6b1ab1ab4Aa
2022042712261288296_j_mathm-2020-0103_ref_028_w2aab3b7c10b1b6b1ab1ac28Aa
2022042712261288296_j_mathm-2020-0103_ref_046_w2aab3b7c10b1b6b1ab1ac46Aa
2022042712261288296_j_mathm-2020-0103_ref_033_w2aab3b7c10b1b6b1ab1ac33Aa
2022042712261288296_j_mathm-2020-0103_ref_015_w2aab3b7c10b1b6b1ab1ac15Aa
2022042712261288296_j_mathm-2020-0103_ref_051_w2aab3b7c10b1b6b1ab1ac51Aa
2022042712261288296_j_mathm-2020-0103_ref_020_w2aab3b7c10b1b6b1ab1ac20Aa
2022042712261288296_j_mathm-2020-0103_ref_003_w2aab3b7c10b1b6b1ab1ab3Aa
2022042712261288296_j_mathm-2020-0103_ref_029_w2aab3b7c10b1b6b1ab1ac29Aa
2022042712261288296_j_mathm-2020-0103_ref_047_w2aab3b7c10b1b6b1ab1ac47Aa
2022042712261288296_j_mathm-2020-0103_ref_016_w2aab3b7c10b1b6b1ab1ac16Aa
2022042712261288296_j_mathm-2020-0103_ref_034_w2aab3b7c10b1b6b1ab1ac34Aa
2022042712261288296_j_mathm-2020-0103_ref_021_w2aab3b7c10b1b6b1ab1ac21Aa
2022042712261288296_j_mathm-2020-0103_ref_006_w2aab3b7c10b1b6b1ab1ab6Aa
2022042712261288296_j_mathm-2020-0103_ref_048_w2aab3b7c10b1b6b1ab1ac48Aa
2022042712261288296_j_mathm-2020-0103_ref_035_w2aab3b7c10b1b6b1ab1ac35Aa
2022042712261288296_j_mathm-2020-0103_ref_017_w2aab3b7c10b1b6b1ab1ac17Aa
2022042712261288296_j_mathm-2020-0103_ref_009_w2aab3b7c10b1b6b1ab1ab9Aa
2022042712261288296_j_mathm-2020-0103_ref_022_w2aab3b7c10b1b6b1ab1ac22Aa
2022042712261288296_j_mathm-2020-0103_ref_040_w2aab3b7c10b1b6b1ab1ac40Aa
2022042712261288296_j_mathm-2020-0103_ref_005_w2aab3b7c10b1b6b1ab1ab5Aa
2022042712261288296_j_mathm-2020-0103_ref_027_w2aab3b7c10b1b6b1ab1ac27Aa
2022042712261288296_j_mathm-2020-0103_ref_045_w2aab3b7c10b1b6b1ab1ac45Aa
2022042712261288296_j_mathm-2020-0103_ref_014_w2aab3b7c10b1b6b1ab1ac14Aa
2022042712261288296_j_mathm-2020-0103_ref_050_w2aab3b7c10b1b6b1ab1ac50Aa
2022042712261288296_j_mathm-2020-0103_ref_032_w2aab3b7c10b1b6b1ab1ac32Aa
2022042712261288296_j_mathm-2020-0103_ref_019_w2aab3b7c10b1b6b1ab1ac19Aa
2022042712261288296_j_mathm-2020-0103_ref_037_w2aab3b7c10b1b6b1ab1ac37Aa
2022042712261288296_j_mathm-2020-0103_ref_024_w2aab3b7c10b1b6b1ab1ac24Aa
2022042712261288296_j_mathm-2020-0103_ref_007_w2aab3b7c10b1b6b1ab1ab7Aa
2022042712261288296_j_mathm-2020-0103_ref_042_w2aab3b7c10b1b6b1ab1ac42Aa
2022042712261288296_j_mathm-2020-0103_ref_011_w2aab3b7c10b1b6b1ab1ac11Aa
2022042712261288296_j_mathm-2020-0103_ref_038_w2aab3b7c10b1b6b1ab1ac38Aa
2022042712261288296_j_mathm-2020-0103_ref_025_w2aab3b7c10b1b6b1ab1ac25Aa
2022042712261288296_j_mathm-2020-0103_ref_043_w2aab3b7c10b1b6b1ab1ac43Aa
2022042712261288296_j_mathm-2020-0103_ref_012_w2aab3b7c10b1b6b1ab1ac12Aa
2022042712261288296_j_mathm-2020-0103_ref_008_w2aab3b7c10b1b6b1ab1ab8Aa
2022042712261288296_j_mathm-2020-0103_ref_030_w2aab3b7c10b1b6b1ab1ac30Aa
2022042712261288296_j_mathm-2020-0103_ref_002_w2aab3b7c10b1b6b1ab1ab2Aa
2022042712261288296_j_mathm-2020-0103_ref_039_w2aab3b7c10b1b6b1ab1ac39Aa
2022042712261288296_j_mathm-2020-0103_ref_026_w2aab3b7c10b1b6b1ab1ac26Aa
2022042712261288296_j_mathm-2020-0103_ref_044_w2aab3b7c10b1b6b1ab1ac44Aa
2022042712261288296_j_mathm-2020-0103_ref_031_w2aab3b7c10b1b6b1ab1ac31Aa
2022042712261288296_j_mathm-2020-0103_ref_013_w2aab3b7c10b1b6b1ab1ac13Aa
References_xml – ident: 2022042712261288296_j_mathm-2020-0103_ref_012_w2aab3b7c10b1b6b1ab1ac12Aa
  doi: 10.1117/12.976517
– ident: 2022042712261288296_j_mathm-2020-0103_ref_039_w2aab3b7c10b1b6b1ab1ac39Aa
  doi: 10.1007/978-3-319-46475-6_10
– ident: 2022042712261288296_j_mathm-2020-0103_ref_004_w2aab3b7c10b1b6b1ab1ab4Aa
  doi: 10.1007/978-3-540-71992-2_87
– ident: 2022042712261288296_j_mathm-2020-0103_ref_003_w2aab3b7c10b1b6b1ab1ab3Aa
– ident: 2022042712261288296_j_mathm-2020-0103_ref_020_w2aab3b7c10b1b6b1ab1ac20Aa
– ident: 2022042712261288296_j_mathm-2020-0103_ref_016_w2aab3b7c10b1b6b1ab1ac16Aa
  doi: 10.1109/ICCV.2015.169
– ident: 2022042712261288296_j_mathm-2020-0103_ref_028_w2aab3b7c10b1b6b1ab1ac28Aa
  doi: 10.1109/ICCV.2013.82
– ident: 2022042712261288296_j_mathm-2020-0103_ref_029_w2aab3b7c10b1b6b1ab1ac29Aa
  doi: 10.1109/CVPRW.2018.00137
– ident: 2022042712261288296_j_mathm-2020-0103_ref_033_w2aab3b7c10b1b6b1ab1ac33Aa
  doi: 10.1016/S0165-1684(99)00161-9
– ident: 2022042712261288296_j_mathm-2020-0103_ref_001_w2aab3b7c10b1b6b1ab1ab1Aa
  doi: 10.1109/CVPRW.2018.00119
– ident: 2022042712261288296_j_mathm-2020-0103_ref_010_w2aab3b7c10b1b6b1ab1ac10Aa
  doi: 10.1145/2651362
– ident: 2022042712261288296_j_mathm-2020-0103_ref_025_w2aab3b7c10b1b6b1ab1ac25Aa
  doi: 10.1109/CVPR.2016.299
– ident: 2022042712261288296_j_mathm-2020-0103_ref_005_w2aab3b7c10b1b6b1ab1ab5Aa
  doi: 10.1007/978-3-319-46478-7_34
– ident: 2022042712261288296_j_mathm-2020-0103_ref_013_w2aab3b7c10b1b6b1ab1ac13Aa
  doi: 10.1016/j.patcog.2020.107246
– ident: 2022042712261288296_j_mathm-2020-0103_ref_018_w2aab3b7c10b1b6b1ab1ac18Aa
  doi: 10.1109/TPAMI.2010.168
– ident: 2022042712261288296_j_mathm-2020-0103_ref_048_w2aab3b7c10b1b6b1ab1ac48Aa
  doi: 10.1109/CVPRW.2018.00135
– ident: 2022042712261288296_j_mathm-2020-0103_ref_051_w2aab3b7c10b1b6b1ab1ac51Aa
  doi: 10.1109/TIP.2015.2446191
– ident: 2022042712261288296_j_mathm-2020-0103_ref_041_w2aab3b7c10b1b6b1ab1ac41Aa
– ident: 2022042712261288296_j_mathm-2020-0103_ref_031_w2aab3b7c10b1b6b1ab1ac31Aa
  doi: 10.1007/978-3-030-14085-4_21
– ident: 2022042712261288296_j_mathm-2020-0103_ref_008_w2aab3b7c10b1b6b1ab1ab8Aa
  doi: 10.1109/TIP.2016.2598681
– ident: 2022042712261288296_j_mathm-2020-0103_ref_019_w2aab3b7c10b1b6b1ab1ac19Aa
  doi: 10.1109/TPAMI.2010.168
– ident: 2022042712261288296_j_mathm-2020-0103_ref_040_w2aab3b7c10b1b6b1ab1ac40Aa
  doi: 10.1007/978-3-319-24574-4_28
– ident: 2022042712261288296_j_mathm-2020-0103_ref_047_w2aab3b7c10b1b6b1ab1ac47Aa
  doi: 10.1109/CVPR.2018.00337
– ident: 2022042712261288296_j_mathm-2020-0103_ref_035_w2aab3b7c10b1b6b1ab1ac35Aa
  doi: 10.1109/ICCV.2015.303
– ident: 2022042712261288296_j_mathm-2020-0103_ref_022_w2aab3b7c10b1b6b1ab1ac22Aa
– ident: 2022042712261288296_j_mathm-2020-0103_ref_038_w2aab3b7c10b1b6b1ab1ac38Aa
  doi: 10.1007/978-3-319-46475-6_10
– ident: 2022042712261288296_j_mathm-2020-0103_ref_023_w2aab3b7c10b1b6b1ab1ac23Aa
– ident: 2022042712261288296_j_mathm-2020-0103_ref_024_w2aab3b7c10b1b6b1ab1ac24Aa
– ident: 2022042712261288296_j_mathm-2020-0103_ref_045_w2aab3b7c10b1b6b1ab1ac45Aa
  doi: 10.1007/978-3-662-03039-4_13
– ident: 2022042712261288296_j_mathm-2020-0103_ref_027_w2aab3b7c10b1b6b1ab1ac27Aa
– ident: 2022042712261288296_j_mathm-2020-0103_ref_026_w2aab3b7c10b1b6b1ab1ac26Aa
  doi: 10.1109/ICCV.2015.388
– ident: 2022042712261288296_j_mathm-2020-0103_ref_011_w2aab3b7c10b1b6b1ab1ac11Aa
  doi: 10.1145/2651362
– ident: 2022042712261288296_j_mathm-2020-0103_ref_046_w2aab3b7c10b1b6b1ab1ac46Aa
  doi: 10.1109/TIP.2003.819861
– ident: 2022042712261288296_j_mathm-2020-0103_ref_009_w2aab3b7c10b1b6b1ab1ab9Aa
– ident: 2022042712261288296_j_mathm-2020-0103_ref_021_w2aab3b7c10b1b6b1ab1ac21Aa
  doi: 10.1109/ICIP.2004.1421765
– ident: 2022042712261288296_j_mathm-2020-0103_ref_044_w2aab3b7c10b1b6b1ab1ac44Aa
  doi: 10.1109/CVPR.2014.383
– ident: 2022042712261288296_j_mathm-2020-0103_ref_030_w2aab3b7c10b1b6b1ab1ac30Aa
  doi: 10.1109/ICDAR.2019.00020
– ident: 2022042712261288296_j_mathm-2020-0103_ref_049_w2aab3b7c10b1b6b1ab1ac49Aa
  doi: 10.1109/TIP.2017.2662206
– ident: 2022042712261288296_j_mathm-2020-0103_ref_002_w2aab3b7c10b1b6b1ab1ab2Aa
  doi: 10.1109/ICIP.2016.7532754
– ident: 2022042712261288296_j_mathm-2020-0103_ref_007_w2aab3b7c10b1b6b1ab1ab7Aa
  doi: 10.1201/9781420027822.ch14
– ident: 2022042712261288296_j_mathm-2020-0103_ref_043_w2aab3b7c10b1b6b1ab1ac43Aa
  doi: 10.1016/0734-189X(86)90004-6
– ident: 2022042712261288296_j_mathm-2020-0103_ref_034_w2aab3b7c10b1b6b1ab1ac34Aa
– ident: 2022042712261288296_j_mathm-2020-0103_ref_050_w2aab3b7c10b1b6b1ab1ac50Aa
  doi: 10.1109/TIP.2018.2839891
– ident: 2022042712261288296_j_mathm-2020-0103_ref_036_w2aab3b7c10b1b6b1ab1ac36Aa
– ident: 2022042712261288296_j_mathm-2020-0103_ref_037_w2aab3b7c10b1b6b1ab1ac37Aa
– ident: 2022042712261288296_j_mathm-2020-0103_ref_014_w2aab3b7c10b1b6b1ab1ac14Aa
  doi: 10.1109/TIP.2017.2691802
– ident: 2022042712261288296_j_mathm-2020-0103_ref_006_w2aab3b7c10b1b6b1ab1ab6Aa
  doi: 10.1109/CVPR.2016.185
– ident: 2022042712261288296_j_mathm-2020-0103_ref_015_w2aab3b7c10b1b6b1ab1ac15Aa
– ident: 2022042712261288296_j_mathm-2020-0103_ref_042_w2aab3b7c10b1b6b1ab1ac42Aa
  doi: 10.1109/34.67627
– ident: 2022042712261288296_j_mathm-2020-0103_ref_017_w2aab3b7c10b1b6b1ab1ac17Aa
– ident: 2022042712261288296_j_mathm-2020-0103_ref_032_w2aab3b7c10b1b6b1ab1ac32Aa
SSID ssib044603931
ssib020483505
ssib022702161
Score 2.0906153
Snippet Mathematical morphology is a powerful tool for image processing tasks. The main difficulty in designing mathematical morphological algorithm is deciding the...
SourceID crossref
walterdegruyter
SourceType Index Database
Publisher
StartPage 87
SubjectTerms 68T07
68T45
68U10
De-Hazing
De-Raining
Dilation Erosion Neurons
Learning structuring element
Morphological Network
Opening-Closing Network
Title Image Restoration by Learning Morphological Opening-Closing Network
URI https://www.degruyter.com/doi/10.1515/mathm-2020-0103
Volume 4
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2353-3390
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssib020483505
  issn: 2353-3390
  databaseCode: M~E
  dateStart: 20160101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1LaxRBEG7W6MFLUFRMjDIHD4IMTr-7j2ETUXAXCRFyG7p7elw1mQm7m5i95F_4f-3HvDIhoIKXYWnoYrbqm6qu6noA8JoRSzSjKi2k802I5TbVUsDUIl8WyUpeCBWGTfD5XJycyM-Tya-2FubylFeVuLqS5_9V1G7NCduXzv6FuDuibsH9dkJ3Tyd29_wjwX8882k4R2FiTJSuO2F-aiMgs9oxtlN4Pp3ErabT0zrEDOYxKXx4Yp11fV19FW-7e_M2bcr6w-3D_uAavBNh7bz9EGA-UtX3HoQHMUjulYlvF139UF1-sC91KOIs6IXSal2vFsOoBMpGUYkDB_Hlxcb3efT_JBqboNUQpjjFOM4IbVUwuYW01dAWR8PcjMe9pfNpaI_hGLE4S5tXyXBv3tor_ZHV63IRvRfkSOSBQO4J5J4AgYLfA_cRp9Lr-9n1YaumfKtjTHs1iXxJH-zLg52D7QueYdNIytF-N3q5G2eg7Z8hL6KwXyPDBseb40dgu_FLkv2Ip8dgYqsnYBqwlAywlOhN0mIpuYGlZISlpMHSU_Dl_eHx9EPaTN1IDcTYH1ksERqWTJDCWFOWrEDSMGGct045tsiUMjMFohYyWXLKNVEKQlYi69SBVPgZ2Krqyj4HiWSoFFowIZkhymQKIm60RVRrIajOdsCblg_5eWyukt8hjh1ARnzKm29uddcWL8Hdf9v2AjzsQb0HttbLC_sSPDCX62-r5auAht_ZgYrA
linkProvider ISSN International Centre
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=Image+Restoration+by+Learning+Morphological+Opening-Closing+Network&rft.jtitle=Mathematical+Morphology+-+Theory+and+Applications&rft.au=Mondal%2C+Ranjan&rft.au=Dey%2C+Moni+Shankar&rft.au=Chanda%2C+Bhabatosh&rft.date=2020-01-01&rft.pub=De+Gruyter+Open&rft.eissn=2353-3390&rft.volume=4&rft.issue=1&rft.spage=87&rft.epage=107&rft_id=info:doi/10.1515%2Fmathm-2020-0103&rft.externalDBID=n%2Fa&rft.externalDocID=10_1515_mathm_2020_01034187
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2353-3390&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2353-3390&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2353-3390&client=summon