REDN: A Recursive Encoder-Decoder Network for Edge Detection

In this paper, we introduce REDN: A Recursive Encoder-Decoder Network with Skip-Connections for edge detection in natural images. The proposed network is a novel integration of a Recursive Neural Network with an Encoder-Decoder architecture. The recursive network enables iterative refinement of the...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE access Ročník 8; s. 90153 - 90164
Hlavní autori: Le, Truc, Duan, Ye
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Piscataway IEEE 2020
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
ISSN:2169-3536, 2169-3536
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract In this paper, we introduce REDN: A Recursive Encoder-Decoder Network with Skip-Connections for edge detection in natural images. The proposed network is a novel integration of a Recursive Neural Network with an Encoder-Decoder architecture. The recursive network enables iterative refinement of the edges using a single network model. Adding skip-connections between encoder and decoder helps the gradients reach all the layers of a network more easily and allows information related to finer details in the early stage of the encoder to be fully utilized in the decoder. Based on our extensive experiments on popular boundary detection datasets including BSDS500 [1], NYUD [2] and Pascal Context [3], REDN significantly advances the state-of-the-art on edge detection regarding standard evaluation metrics such as Optimal Dataset Scale (ODS) F-measure, Optimal Image Scale (OIS) F-measure, and Average Precision (AP).
AbstractList In this paper, we introduce REDN: A Recursive Encoder-Decoder Network with Skip-Connections for edge detection in natural images. The proposed network is a novel integration of a Recursive Neural Network with an Encoder-Decoder architecture. The recursive network enables iterative refinement of the edges using a single network model. Adding skip-connections between encoder and decoder helps the gradients reach all the layers of a network more easily and allows information related to finer details in the early stage of the encoder to be fully utilized in the decoder. Based on our extensive experiments on popular boundary detection datasets including BSDS500 [1], NYUD [2] and Pascal Context [3], REDN significantly advances the state-of-the-art on edge detection regarding standard evaluation metrics such as Optimal Dataset Scale (ODS) F-measure, Optimal Image Scale (OIS) F-measure, and Average Precision (AP).
In this paper, we introduce REDN: A Recursive Encoder-Decoder Network with Skip-Connections for edge detection in natural images. The proposed network is a novel integration of a Recursive Neural Network with an Encoder-Decoder architecture. The recursive network enables iterative refinement of the edges using a single network model. Adding skip-connections between encoder and decoder helps the gradients reach all the layers of a network more easily and allows information related to finer details in the early stage of the encoder to be fully utilized in the decoder. Based on our extensive experiments on popular boundary detection datasets including BSDS500 [1], NYUD [2] and Pascal Context [3], REDN significantly advances the state-of-the-art on edge detection regarding standard evaluation metrics such as Optimal Dataset Scale (ODS) F-measure, Optimal Image Scale (OIS) F-measure, and Average Precision (AP).In this paper, we introduce REDN: A Recursive Encoder-Decoder Network with Skip-Connections for edge detection in natural images. The proposed network is a novel integration of a Recursive Neural Network with an Encoder-Decoder architecture. The recursive network enables iterative refinement of the edges using a single network model. Adding skip-connections between encoder and decoder helps the gradients reach all the layers of a network more easily and allows information related to finer details in the early stage of the encoder to be fully utilized in the decoder. Based on our extensive experiments on popular boundary detection datasets including BSDS500 [1], NYUD [2] and Pascal Context [3], REDN significantly advances the state-of-the-art on edge detection regarding standard evaluation metrics such as Optimal Dataset Scale (ODS) F-measure, Optimal Image Scale (OIS) F-measure, and Average Precision (AP).
Author Le, Truc
Duan, Ye
Author_xml – sequence: 1
  givenname: Truc
  surname: Le
  fullname: Le, Truc
  organization: Department of EECS, University of Missouri, Columbia, MO, USA
– sequence: 2
  givenname: Ye
  orcidid: 0000-0002-1166-7703
  surname: Duan
  fullname: Duan, Ye
  email: duanye@missouri.edu
  organization: Department of EECS, University of Missouri, Columbia, MO, USA
BookMark eNp9kU1v1DAQhi1UREvpL-glEhcuWfwZrxFCWu2mpVJVpBbOlj8mi5ds3DpJEf8e72ZBtAd88FjjeZ-x532NjrrYAULnBM8Iwer9Yrms7-5mFFM8o0pxUuEX6ISSSpVMsOron_MxOuv7Dc5rnlNCvkLHjApOiRQn6ONtvbr5UCyKW3Bj6sMjFHXnoodUrmAfixsYfsb0o2hiKmq_hmIFA7ghxO4NetmYtoezQzxF3y7qr8vP5fWXy6vl4rp0XFVDaUTDHSHcecp5Yw2YvFmGBePUKiYpt576hjaVEV5hQkUD3nNLuQBvnGWn6Gri-mg2-j6FrUm_dDRB7xMxrbVJQ3AtaOl4VVErqTGeK2mNcJk-9zI3UpapzPo0se5HuwXvoBuSaZ9An9504btex0ctqRKE0Qx4dwCk-DBCP-ht6B20rekgjr2mnDClxHwucunbZ6WbOKYujypXCU4wFfsXqanKpdj3CRrtwmB28839Q6sJ1jvL9WS53lmuD5ZnLXum_fOR_6vOJ1UAgL8KhRWRCrPfynK3Vw
CODEN IAECCG
CitedBy_id crossref_primary_10_1007_s11063_023_11323_z
crossref_primary_10_1002_cav_2051
crossref_primary_10_1007_s00521_024_10936_2
crossref_primary_10_1038_s41598_023_50899_3
crossref_primary_10_1007_s11760_024_03795_w
crossref_primary_10_1016_j_patcog_2023_109361
crossref_primary_10_3390_app13021034
crossref_primary_10_1007_s11760_021_01899_1
crossref_primary_10_1109_TAI_2022_3223893
crossref_primary_10_1109_TGRS_2025_3529134
crossref_primary_10_3389_fnbot_2025_1550939
crossref_primary_10_1007_s11220_021_00351_5
crossref_primary_10_1016_j_neucom_2022_02_079
crossref_primary_10_1016_j_compmedimag_2024_102417
crossref_primary_10_3390_electronics13173540
Cites_doi 10.1109/CVPR.2014.49
10.1109/TPAMI.2007.1144
10.1109/CVPR.2019.01133
10.1109/CVPR.2017.191
10.1023/B:VISI.0000022288.19776.77
10.1109/ICCV.2011.6126343
10.1109/CVPR.2016.90
10.1109/TPAMI.2014.2377715
10.1109/ICCV.2015.164
10.1023/A:1011174803800
10.1098/rspb.1980.0020
10.1007/978-3-642-33718-5_56
10.1109/CVPR.2018.00474
10.1109/CVPR.2015.7299067
10.5244/C.29.110
10.1109/CVPR.2015.7298594
10.1109/CVPR.2017.622
10.1109/CVPR.2018.00716
10.1109/ACCESS.2020.2981720
10.1109/CVPR.1999.786963
10.1109/34.1000236
10.1109/ICCV.2015.304
10.1109/TAC.1974.1100577
10.1109/34.56205
10.1109/TPAMI.2012.231
10.1109/CVPR.2017.195
10.1109/TPAMI.2010.161
10.1109/CVPR.2006.298
10.1109/T-C.1975.224274
10.1109/CVPR.2017.187
10.1109/34.99234
10.1109/TPAMI.1986.4767769
10.1109/TPAMI.1986.4767851
10.1007/978-3-319-46448-0_3
10.1109/CVPR.2016.488
10.1117/12.7972120
10.1109/CVPR.2015.7298965
10.1007/978-3-030-01231-1_35
10.1109/CVPR.2016.181
10.1109/CVPR.2019.00395
10.1109/TPAMI.2017.2700300
10.1109/CVPR.2015.7298782
10.1007/s11263-017-1004-z
10.1007/978-3-030-01219-9_24
10.1109/TPAMI.2016.2599174
10.1109/TPAMI.2014.17
10.1007/978-3-540-88690-7_4
10.1109/CVPR.2007.383343
10.1109/TPAMI.2016.2577031
10.1109/CVPR.2014.119
10.1109/CVPR.2018.00031
10.1109/CVPR.2015.7298652
10.1109/TPAMI.2004.1273918
10.1109/CVPR.2018.00346
10.1109/CVPR.2017.243
10.1109/ICMLA.2011.102
10.1007/978-3-642-15552-9_47
10.1109/ICCV.2015.178
10.24963/ijcai.2019/110
10.1109/CVPR.2013.262
10.1109/CVPR.2015.7298651
10.1109/CVPR.2013.406
10.1109/CVPR.2016.28
10.1109/34.93808
10.1007/BF00133570
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020
DBID 97E
ESBDL
RIA
RIE
AAYXX
CITATION
7SC
7SP
7SR
8BQ
8FD
JG9
JQ2
L7M
L~C
L~D
7X8
5PM
DOA
DOI 10.1109/ACCESS.2020.2994160
DatabaseName IEEE Xplore (IEEE)
IEEE Xplore Open Access Journals
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
Computer and Information Systems Abstracts
Electronics & Communications Abstracts
Engineered Materials Abstracts
METADEX
Technology Research Database
Materials Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
MEDLINE - Academic
PubMed Central (Full Participant titles)
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
Materials Research Database
Engineered Materials Abstracts
Technology Research Database
Computer and Information Systems Abstracts – Academic
Electronics & Communications Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Advanced Technologies Database with Aerospace
METADEX
Computer and Information Systems Abstracts Professional
MEDLINE - Academic
DatabaseTitleList
MEDLINE - Academic

Materials Research Database

Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
– sequence: 2
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
– sequence: 3
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 2169-3536
EndPage 90164
ExternalDocumentID oai_doaj_org_article_7c4662b72aad497ba5c4bd8d7b939b39
PMC7295132
10_1109_ACCESS_2020_2994160
9091790
Genre orig-research
GrantInformation_xml – fundername: National Institute of Biomedical Imaging and Bioengineering
  grantid: R03-EB028427
  funderid: 10.13039/100000070
GroupedDBID 0R~
4.4
5VS
6IK
97E
AAJGR
ABAZT
ABVLG
ACGFS
ADBBV
AGSQL
ALMA_UNASSIGNED_HOLDINGS
BCNDV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
EBS
EJD
ESBDL
GROUPED_DOAJ
IPLJI
JAVBF
KQ8
M43
M~E
O9-
OCL
OK1
RIA
RIE
RNS
AAYXX
CITATION
7SC
7SP
7SR
8BQ
8FD
JG9
JQ2
L7M
L~C
L~D
7X8
5PM
ID FETCH-LOGICAL-c496t-a5f4c114cd244fbaeafbab305342b93724bd2df2f6a5d90125fedd4b245edacb3
IEDL.DBID DOA
ISICitedReferencesCount 14
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000538727700103&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2169-3536
IngestDate Fri Oct 03 12:21:05 EDT 2025
Tue Sep 30 15:52:25 EDT 2025
Thu Oct 02 07:12:32 EDT 2025
Sun Jun 29 15:37:20 EDT 2025
Sat Nov 29 02:42:25 EST 2025
Tue Nov 18 22:52:10 EST 2025
Wed Aug 27 02:30:46 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Language English
License https://creativecommons.org/licenses/by/4.0/legalcode
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c496t-a5f4c114cd244fbaeafbab305342b93724bd2df2f6a5d90125fedd4b245edacb3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ORCID 0000-0002-1166-7703
OpenAccessLink https://doaj.org/article/7c4662b72aad497ba5c4bd8d7b939b39
PMID 32542175
PQID 2454102539
PQPubID 4845423
PageCount 12
ParticipantIDs crossref_citationtrail_10_1109_ACCESS_2020_2994160
proquest_miscellaneous_2413995885
ieee_primary_9091790
proquest_journals_2454102539
crossref_primary_10_1109_ACCESS_2020_2994160
pubmedcentral_primary_oai_pubmedcentral_nih_gov_7295132
doaj_primary_oai_doaj_org_article_7c4662b72aad497ba5c4bd8d7b939b39
PublicationCentury 2000
PublicationDate 20200000
2020-00-00
20200101
2020-01-01
PublicationDateYYYYMMDD 2020-01-01
PublicationDate_xml – year: 2020
  text: 20200000
PublicationDecade 2020
PublicationPlace Piscataway
PublicationPlace_xml – name: Piscataway
PublicationTitle IEEE access
PublicationTitleAbbrev Access
PublicationYear 2020
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref56
ref59
ref15
shi (ref35) 2016
ref58
ref14
ref53
ref52
ref55
ref11
howard (ref86) 2017
ref54
ref17
ref16
chen (ref18) 2015
ref19
maas (ref74) 2013
duda (ref42) 1973
ren (ref57) 2012
ref51
ref50
ref90
ref46
ref89
ref45
ref48
ref47
ref44
ref87
poma (ref32) 2020
ref8
ref7
ref9
ref4
ref3
simonyan (ref13) 2014
ref6
ref5
ref82
ronneberger (ref36) 2015
xu (ref66) 2017
ref81
ref40
kingma (ref76) 2014
ref80
ref79
krizhevsky (ref12) 2012
ref78
ref34
kokkinos (ref10) 2016
ref37
nathan silberman (ref2) 2012
ref31
ref30
ref77
ref33
abadi (ref75) 2015
ref1
ref39
ref38
ioffe (ref73) 2015
kivinen (ref60) 2014; 33
iandola (ref88) 2016
ganin (ref83) 2015
shen (ref63) 2015
ref71
ref70
ref72
badrinarayanan (ref20) 2015
ziou (ref49) 1998; 8
ref68
ref24
ref67
ref23
gupta (ref85) 2014
ref26
ref69
ref25
ref64
hwang (ref84) 2015
marr (ref43) 1980; 207
ref22
ref65
ref21
ref28
sobel (ref41) 0
ref27
ref29
ref62
ref61
References_xml – year: 2016
  ident: ref88
  article-title: SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and < 0.5MB model size
  publication-title: arXiv 1602 07360
– ident: ref80
  doi: 10.1109/CVPR.2014.49
– start-page: 3982
  year: 2015
  ident: ref63
  article-title: DeepContour: A deep convolutional feature learned by positive-sharing loss for contour detection
  publication-title: Proc IEEE Conf Comput Vis Pattern Recognit (CVPR)
– ident: ref8
  doi: 10.1109/TPAMI.2007.1144
– ident: ref70
  doi: 10.1109/CVPR.2019.01133
– ident: ref30
  doi: 10.1109/CVPR.2017.191
– ident: ref78
  doi: 10.1023/B:VISI.0000022288.19776.77
– ident: ref69
  doi: 10.1109/ICCV.2011.6126343
– start-page: 1
  year: 2014
  ident: ref76
  article-title: Adam: A method for stochastic optimization
  publication-title: Proc IEEE Int Conf Learn Represent
– ident: ref38
  doi: 10.1109/CVPR.2016.90
– start-page: 3961
  year: 2017
  ident: ref66
  article-title: Learning deep structured multi-scale features using attention-gated crfs for contour prediction
  publication-title: Advances Neural Information Processing Systems
– ident: ref59
  doi: 10.1109/TPAMI.2014.2377715
– ident: ref25
  doi: 10.1109/ICCV.2015.164
– ident: ref9
  doi: 10.1023/A:1011174803800
– volume: 207
  start-page: 187
  year: 1980
  ident: ref43
  article-title: Theory of edge detection
  publication-title: Proc Roy Soc London B Biol Sci
  doi: 10.1098/rspb.1980.0020
– ident: ref55
  doi: 10.1007/978-3-642-33718-5_56
– ident: ref87
  doi: 10.1109/CVPR.2018.00474
– ident: ref62
  doi: 10.1109/CVPR.2015.7299067
– ident: ref82
  doi: 10.5244/C.29.110
– year: 2016
  ident: ref35
  article-title: Learning non-lambertian object intrinsics across ShapeNet categories
  publication-title: arXiv 1612 08510
– ident: ref14
  doi: 10.1109/CVPR.2015.7298594
– year: 2015
  ident: ref20
  article-title: SegNet: A deep convolutional encoder-decoder architecture for image segmentation
  publication-title: arXiv 1511 00561
– year: 1973
  ident: ref42
  publication-title: Pattern Classification Scene Analysis
– ident: ref28
  doi: 10.1109/CVPR.2017.622
– ident: ref89
  doi: 10.1109/CVPR.2018.00716
– ident: ref90
  doi: 10.1109/ACCESS.2020.2981720
– ident: ref48
  doi: 10.1109/CVPR.1999.786963
– ident: ref77
  doi: 10.1109/34.1000236
– ident: ref22
  doi: 10.1109/ICCV.2015.304
– ident: ref4
  doi: 10.1109/TAC.1974.1100577
– ident: ref46
  doi: 10.1109/34.56205
– start-page: 345
  year: 2014
  ident: ref85
  article-title: Learning rich features from RGB-D images for object detection and segmentation
  publication-title: Proc IEEE Eur Conf Comput Vis
– ident: ref16
  doi: 10.1109/TPAMI.2012.231
– ident: ref33
  doi: 10.1109/CVPR.2017.195
– ident: ref1
  doi: 10.1109/TPAMI.2010.161
– ident: ref51
  doi: 10.1109/CVPR.2006.298
– start-page: 234
  year: 2015
  ident: ref36
  article-title: U-Net: Convolutional networks for biomedical image segmentation
  publication-title: Proc Med Image Comput Comput -Assist Intervent
– ident: ref5
  doi: 10.1109/T-C.1975.224274
– ident: ref27
  doi: 10.1109/CVPR.2017.187
– start-page: 746
  year: 2012
  ident: ref2
  article-title: Indoor segmentation and support inference from RGBD images
  publication-title: Proc Eur Conf Comput Vis
– ident: ref7
  doi: 10.1109/34.99234
– ident: ref44
  doi: 10.1109/TPAMI.1986.4767769
– ident: ref45
  doi: 10.1109/TPAMI.1986.4767851
– year: 2015
  ident: ref75
  publication-title: TensorFlow Large-Scale Machine Learning on Heterogeneous Systems
– ident: ref39
  doi: 10.1007/978-3-319-46448-0_3
– ident: ref37
  doi: 10.1109/CVPR.2016.488
– ident: ref6
  doi: 10.1117/12.7972120
– start-page: 271
  year: 0
  ident: ref41
  article-title: A $3\times3$ isotropic gradient operator for image processing
  publication-title: Pattern Classification and Scene Analysis
– ident: ref19
  doi: 10.1109/CVPR.2015.7298965
– volume: 33
  start-page: 512
  year: 2014
  ident: ref60
  article-title: Visual boundary prediction: A deep neural prediction network and quality dissection
  publication-title: Proc 17th Int Conf Artif Intell Statist
– ident: ref65
  doi: 10.1007/978-3-030-01231-1_35
– ident: ref40
  doi: 10.1109/CVPR.2016.181
– start-page: 3
  year: 2013
  ident: ref74
  article-title: Rectifier nonlinearities improve neural network acoustic models
  publication-title: Proc IEEE Int Conf Mach Learn
– ident: ref31
  doi: 10.1109/CVPR.2019.00395
– ident: ref29
  doi: 10.1109/TPAMI.2017.2700300
– ident: ref81
  doi: 10.1109/CVPR.2015.7298782
– ident: ref64
  doi: 10.1007/s11263-017-1004-z
– ident: ref68
  doi: 10.1007/978-3-030-01219-9_24
– year: 2017
  ident: ref86
  article-title: MobileNets: Efficient convolutional neural networks for mobile vision applications
  publication-title: arXiv 1704 04861
– start-page: 584
  year: 2012
  ident: ref57
  article-title: Discriminatively trained sparse code gradients for contour detection
  publication-title: Proc Int Conf Neural Inf Process
– start-page: 1
  year: 2015
  ident: ref84
  article-title: Pixel-wise deep learning for contour detection
  publication-title: Proc IEEE Int Conf Learn Represent
– ident: ref24
  doi: 10.1109/TPAMI.2016.2599174
– ident: ref56
  doi: 10.1109/TPAMI.2014.17
– start-page: 1
  year: 2015
  ident: ref18
  article-title: Semantic image segmentation with deep convolutional nets and fully connected CRFS
  publication-title: Proc Int Conf Learn Represent
– ident: ref53
  doi: 10.1007/978-3-540-88690-7_4
– start-page: 1923
  year: 2020
  ident: ref32
  article-title: Dense extreme inception network: Towards a robust CNN model for edge detection
  publication-title: Proc IEEE Winter Conf Appl Comput Vis (WACV)
– ident: ref52
  doi: 10.1109/CVPR.2007.383343
– ident: ref15
  doi: 10.1109/TPAMI.2016.2577031
– ident: ref3
  doi: 10.1109/CVPR.2014.119
– start-page: 1097
  year: 2012
  ident: ref12
  article-title: Imagenet classification with deep convolutional neural networks
  publication-title: Proc Adv Neural Inf Process Syst
– ident: ref72
  doi: 10.1109/CVPR.2018.00031
– ident: ref23
  doi: 10.1109/CVPR.2015.7298652
– start-page: 536
  year: 2015
  ident: ref83
  article-title: N4-fields: Neural network nearest neighbor fields for image transforms
  publication-title: Proc Asian Conf Comput Vis
– ident: ref50
  doi: 10.1109/TPAMI.2004.1273918
– start-page: 1
  year: 2016
  ident: ref10
  article-title: Pushing the boundaries of boundary detection using deep learning
  publication-title: Proc Int Conf Learn Represent
– ident: ref71
  doi: 10.1109/CVPR.2018.00346
– start-page: 1
  year: 2015
  ident: ref73
  article-title: Batch normalization: Accelerating deep network training by reducing internal covariate shift
  publication-title: Proc Int Conf Mach Learn
– ident: ref34
  doi: 10.1109/CVPR.2017.243
– ident: ref61
  doi: 10.1109/ICMLA.2011.102
– ident: ref54
  doi: 10.1007/978-3-642-15552-9_47
– ident: ref21
  doi: 10.1109/ICCV.2015.178
– start-page: 1
  year: 2014
  ident: ref13
  article-title: Very deep convolutional networks for large-scale image recognition
  publication-title: Proc Int Conf Learn Represent
– ident: ref67
  doi: 10.24963/ijcai.2019/110
– ident: ref79
  doi: 10.1109/CVPR.2013.262
– ident: ref17
  doi: 10.1109/CVPR.2015.7298651
– ident: ref58
  doi: 10.1109/CVPR.2013.406
– volume: 8
  start-page: 537
  year: 1998
  ident: ref49
  article-title: Edge detection techniques-An overview
  publication-title: Int J Pattern Recognit Image Anal
– ident: ref26
  doi: 10.1109/CVPR.2016.28
– ident: ref47
  doi: 10.1109/34.93808
– ident: ref11
  doi: 10.1007/BF00133570
SSID ssj0000816957
Score 2.290908
Snippet In this paper, we introduce REDN: A Recursive Encoder-Decoder Network with Skip-Connections for edge detection in natural images. The proposed network is a...
SourceID doaj
pubmedcentral
proquest
crossref
ieee
SourceType Open Website
Open Access Repository
Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 90153
SubjectTerms Coders
Convolution
Datasets
Decoding
deep learning
Detectors
Edge detection
encoder-decoder network
Encoders-Decoders
Fuses
Image edge detection
Iterative methods
Machine learning
Neural networks
recursive network
Task analysis
SummonAdditionalLinks – databaseName: IEEE Electronic Library (IEL)
  dbid: RIE
  link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT9wwELYA9dAegBYqtgWUShwJJI4d26iXZXdRTyuEWomb5VcoEsqiZZffz4xjIiJVlbgkUWxHMx5P_I09niHkRFoqpDfoViVZzkofclsFmVfKlcoAJK0aH5NNiPlc3t6q6w1y2p-FCSFE57Nwho9xL98v3BqXys4VTG5CgYG-KUTdndXq11MwgYTiIgUWKgt1Pp5MgAcwAWlxBj9dQB7FYPKJMfpTUpUBvhx6R76Zbq523kfoLtlOsDIbd-PgM9kI7Rfy6U2wwT3y82Y2nV9k4-wGl9jRaz2btXiifZlPQ7xn884nPAMgm838XcimYRVdtdp98udq9nvyK0-5E3LHVL3KDW-YA1vHeZi_G2uCgYsF5a4YtQBJKLOe-oY2teEeMAHlTfCeWcp48MbZ6ivZahdtOEDnp8IYT5WMiUkqr6Q1ZeMaXlthK8VHhL52qnYpsDjmt3jQ0cAolO4koVESOkliRE77Ro9dXI3_V79EafVVMSh2fAHdrpOOaeFYXVMrKJDLlLCGO-BSegEMK6B0RPZQVP1HkpRG5PBV9jop8JOGfmCAvTi2-tEXg-rhfoppw2KNdUo8GCwldIEYjJkBncOS9v5vDOINRg0vK_rt3zR9Jx-R_W6t55BsrZbrcEQ-uOfV_dPyOI78F8moAkE
  priority: 102
  providerName: IEEE
Title REDN: A Recursive Encoder-Decoder Network for Edge Detection
URI https://ieeexplore.ieee.org/document/9091790
https://www.proquest.com/docview/2454102539
https://www.proquest.com/docview/2413995885
https://pubmed.ncbi.nlm.nih.gov/PMC7295132
https://doaj.org/article/7c4662b72aad497ba5c4bd8d7b939b39
Volume 8
WOSCitedRecordID wos000538727700103&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: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 2169-3536
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000816957
  issn: 2169-3536
  databaseCode: DOA
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2169-3536
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000816957
  issn: 2169-3536
  databaseCode: M~E
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3NS8MwFA86POhB_MTpHBU8Wm3TpEnEy9wqXhwiCruFfFUFqTKnR_92X9I61otevLTQfJD88pL3Xvo-EDrmGjNulTer4iQmqXWxzhyPM2FSoUAkzUobkk2w8ZhPJuJ2IdWXtwmrwwPXwJ0xQ_Ica4aVskQwragh2nLLtMiEzoLrXsLEgjIVzmCe5oKyJsxQmoizwXAIMwKFECencASDHJK0WFGI2N-kWGlJm21byQXmc7WB1hupMRrUo91ES67aQmsLsQS30cVdMRqfR4Pozt-ge6P0qKi8w_o0Hrnwjsa1yXcEcmpU2EcXjdwsWGJVO-jhqrgfXsdNaoTYEJHPYkVLYkCVMRbYc6mVU_DQsHczggEYhgEjbEtc5opaYPmYls5aojGhziqjs13UqV4rt-dtmxKAFgse8o5kVnCt0tKUNNcM8KVdhH9QkqaJG-7TV7zIoD8kQtbQSg-tbKDtopN5o7c6bMbv1S89_POqPuZ1-ACUIBtKkH9RQhdt-8WbdyJAFGIC-u79LKZs9ue7BBwIiFbUtzqaF8PO8r9LVOVeP3yd1Pv9cg4QsBYRtMbZLqmen0KMbtBZKCj6-_8xsQO06sGqL356qDObfrhDtGI-Z8_v0z5aZhPeD-QPz5uvoh-cGL8BF_kIzg
linkProvider Directory of Open Access Journals
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlR3va9UwMIxNUD9s6hw-nVrBj-vWpkmTiF_e3ntj4iwyJuxbyK_qQPrk7T3_fu_SrKwggl_a0iTlcpfr_cjljpD30lIhvcGwKslyVvqQ2yrIvFKuVAZU0qr1sdiEaBp5fa2-bpGj4SxMCCEGn4VjfIx7-X7pNugqO1Eg3IQCA30HK2el01qDRwVLSCguUmqhslAn09kMZgFGIC2O4bcLukcxEj8xS38qqzLSMMfxkfcEztne_4H6hOwmxTKb9ivhKdkK3TPy-F66wX3y8XIxbz5k0-wSnewYt54tOjzTvsrnId6zpo8Kz0CVzRb-e8jmYR2Dtbrn5NvZ4mp2nqfqCbljql7nhrfMgbXjPEjw1ppg4GKBvStGLSgllFlPfUvb2nAPWgHlbfCeWcp48MbZ6oBsd8suvMDwp8IYT5WMpUkqr6Q1ZetaXlthK8UnhN4hVbuUWhwrXPzU0cQolO4poZESOlFiQo6GQb_6zBr_7n6K1Bq6Ylrs-ALQrhOXaeFYXVMrKIDLlLCGO5il9AImrADSCdlHUg0fSVSakMM72uvEwrca8MBA--I46t3QDMyHOyqmC8sN9inxaLCUgAIxWjMjOMct3c2PmMYbzBpeVvTl32F6Sx6eX3250Befms-vyCNERe_5OSTb69UmvCYP3O_1ze3qTeSCP1oPBYo
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=REDN%3A+A+Recursive+Encoder-Decoder+Network+for+Edge+Detection&rft.jtitle=IEEE+access&rft.au=Le%2C+Truc&rft.au=Duan%2C+Ye&rft.date=2020&rft.issn=2169-3536&rft.eissn=2169-3536&rft.volume=8&rft.spage=90153&rft.epage=90164&rft_id=info:doi/10.1109%2FACCESS.2020.2994160&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_ACCESS_2020_2994160
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2169-3536&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2169-3536&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2169-3536&client=summon