Fused Text Segmentation Networks for Multi-oriented Scene Text Detection

In this paper, we introduce a novel end-end framework for multi-oriented scene text detection from an instance-aware semantic segmentation perspective. We present Fused Text Segmentation Networks, which combine multi-level features during the feature extracting as text instance may rely on finer fea...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2018 24th International Conference on Pattern Recognition (ICPR) S. 3604 - 3609
Hauptverfasser: Dai, Yuchen, Huang, Zheng, Gao, Yuting, Xu, Youxuan, Chen, Kai, Guo, Jie, Qiu, Weidong
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.08.2018
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract In this paper, we introduce a novel end-end framework for multi-oriented scene text detection from an instance-aware semantic segmentation perspective. We present Fused Text Segmentation Networks, which combine multi-level features during the feature extracting as text instance may rely on finer feature expression compared to general objects. It detects and segments the text instance jointly and simultaneously, leveraging merits from both semantic segmentation task and region proposal based object detection task. Not involving any extra pipelines, our approach surpasses the current state of the art on multi-oriented scene text detection benchmarks: ICDAR2015 Incidental Scene Text and MSRA-TD500 reaching Hmean 84.1 % and 82.0 % respectively. Morever, we report a baseline on total-text containing curved text which suggests effectiveness of the proposed approach.
AbstractList In this paper, we introduce a novel end-end framework for multi-oriented scene text detection from an instance-aware semantic segmentation perspective. We present Fused Text Segmentation Networks, which combine multi-level features during the feature extracting as text instance may rely on finer feature expression compared to general objects. It detects and segments the text instance jointly and simultaneously, leveraging merits from both semantic segmentation task and region proposal based object detection task. Not involving any extra pipelines, our approach surpasses the current state of the art on multi-oriented scene text detection benchmarks: ICDAR2015 Incidental Scene Text and MSRA-TD500 reaching Hmean 84.1 % and 82.0 % respectively. Morever, we report a baseline on total-text containing curved text which suggests effectiveness of the proposed approach.
Author Guo, Jie
Dai, Yuchen
Qiu, Weidong
Chen, Kai
Huang, Zheng
Gao, Yuting
Xu, Youxuan
Author_xml – sequence: 1
  givenname: Yuchen
  surname: Dai
  fullname: Dai, Yuchen
  organization: School of Electronic Information and Electrical, Shanghai Jiao Tong University, Shanghai, China
– sequence: 2
  givenname: Zheng
  surname: Huang
  fullname: Huang, Zheng
  organization: School of Electronic Information and Electrical, Shanghai Jiao Tong University, Shanghai, China
– sequence: 3
  givenname: Yuting
  surname: Gao
  fullname: Gao, Yuting
  organization: School of Electronic Information and Electrical, Shanghai Jiao Tong University, Shanghai, China
– sequence: 4
  givenname: Youxuan
  surname: Xu
  fullname: Xu, Youxuan
  organization: Xiamen No. 1 High School, Fujian, China
– sequence: 5
  givenname: Kai
  surname: Chen
  fullname: Chen, Kai
  organization: School of Electronic Information and Electrical, Shanghai Jiao Tong University, Shanghai, China
– sequence: 6
  givenname: Jie
  surname: Guo
  fullname: Guo, Jie
  organization: School of Electronic Information and Electrical, Shanghai Jiao Tong University, Shanghai, China
– sequence: 7
  givenname: Weidong
  surname: Qiu
  fullname: Qiu, Weidong
  organization: School of Electronic Information and Electrical, Shanghai Jiao Tong University, Shanghai, China
BookMark eNotj8tOwzAQRY0EElDyAYhNfiBlxo7tyRIF-pDKQ7SsK8eZIEOboMQV8PcUtau7OPdc6V6K07ZrWYhrhDEiFLfz8uV1LAFpTDo3YMyJSApLqBUZZYnUuUiG4QMApCGVK7gQs8lu4Dpd8U9Ml_y-5Ta6GLo2feL43fWfQ9p0ffq428SQdX3Y43176bnlg3PPkf2_cCXOGrcZODnmSLxNHlblLFs8T-fl3SILMseYETppJGrNnhErw6a2NVSFMY3mwnogrrhCr9kqVUGdM_lcOlCKsGmcVSNxc9gNzLz-6sPW9b_r41_1BzbYTV0
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/ICPR.2018.8546066
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Xplore : IEEE Electronic Library (IEL) [unlimited simultaenous users]
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
EISBN 9781538637883
153863788X
EndPage 3609
ExternalDocumentID 8546066
Genre orig-research
GroupedDBID 6IE
6IF
6IL
6IN
AAJGR
AAWTH
ABLEC
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
IEGSK
OCL
RIB
RIC
RIE
RIL
ID FETCH-LOGICAL-i241t-81a262155ece11b6e6d7d0b966f5e97c08ebeb1c5e733b0d4e8c42a03381ffa73
IEDL.DBID RIE
ISICitedReferencesCount 86
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000455146803101&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:51:53 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i241t-81a262155ece11b6e6d7d0b966f5e97c08ebeb1c5e733b0d4e8c42a03381ffa73
PageCount 6
ParticipantIDs ieee_primary_8546066
PublicationCentury 2000
PublicationDate 2018-08
PublicationDateYYYYMMDD 2018-08-01
PublicationDate_xml – month: 08
  year: 2018
  text: 2018-08
PublicationDecade 2010
PublicationTitle 2018 24th International Conference on Pattern Recognition (ICPR)
PublicationTitleAbbrev ICPR
PublicationYear 2018
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0002683430
Score 2.4414914
Snippet In this paper, we introduce a novel end-end framework for multi-oriented scene text detection from an instance-aware semantic segmentation perspective. We...
SourceID ieee
SourceType Publisher
StartPage 3604
SubjectTerms Benchmark testing
Feature extraction
Object detection
Pipelines
Semantics
Task analysis
Title Fused Text Segmentation Networks for Multi-oriented Scene Text Detection
URI https://ieeexplore.ieee.org/document/8546066
WOSCitedRecordID wos000455146803101&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
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV09T8MwED2VioGpQIv4VgZG0saJP-dCVZaqgiJ1q2zngjqQoibl92M7oQiJhc2ydLJ0J_udfe_5AO4MT4VWXvZLUxpTRjDWmpgYNWcMuabC6NBsQsxmcrlU8w7c77UwiBjIZzj0w1DLzzd255_KRpJRn28fwIEQotFq7d9TUi4zmn0XLkmiRk_j-bPnbslha_ergUrAj0nvfysfw-BHiBfN9xBzAh0sT6HXZo5Ruy-rPkwnu8pNLNxJG73g23srKCqjWcPyriKXm0ZBbBtv_M_GdTB351xj84B1oGSVA3idPC7G07jtkRCvHfbWsSQ65Q62GVokxHDkucgT4y4xBUMlbCJdlAyxDEWWmSSnKC1NdeJupqQotMjOoFtuSjyHyArKJbNpwXNGqSo0UTkhBVEaXV4h0wvoe8esPppvMFatTy7_nr6CI-_7hit3Dd16u8MbOLSf9bra3obYfQE8I5sj
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT8MwDLbGQILTgA3xpgeOdGvavHoeTJsY0wRD2m1KUxftQIfWjt9PkpYhJC7cokhWJFuxHfv7YoDbhIdCxZb2S0PqU0bQV4okPirOGHJFRaLcsAkxmcj5PJ424G7LhUFEBz7Drl26Xn660htbKutJRm2-vQO7jNKQVGytbUUl5DKi0XfrkgRxb9SfPlv0luzWkr9GqLgIMmj97-xD6PxQ8bzpNsgcQQPzY2jVuaNX38yiDcPBpjAbM-NrvRd8e68pRbk3qXDehWeyU8_Rbf2V_du4dOLG01Uy91g6UFbegdfBw6w_9OspCf7SRN_Sl0SF3ARuhhoJSTjyVKRBYp4xGcNY6EAaOyVEMxRRlAQpRalpqALzNiVZpkR0As18leMpeFpQLpkOM54aBceZInFKSEZihSazkOEZtK1iFh_VRxiLWifnf2_fwP5w9jRejEeTxws4sHaokHOX0CzXG7yCPf1ZLov1tbPjF31Vnmo
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%3Abook&rft.genre=proceeding&rft.title=2018+24th+International+Conference+on+Pattern+Recognition+%28ICPR%29&rft.atitle=Fused+Text+Segmentation+Networks+for+Multi-oriented+Scene+Text+Detection&rft.au=Dai%2C+Yuchen&rft.au=Huang%2C+Zheng&rft.au=Gao%2C+Yuting&rft.au=Xu%2C+Youxuan&rft.date=2018-08-01&rft.pub=IEEE&rft.spage=3604&rft.epage=3609&rft_id=info:doi/10.1109%2FICPR.2018.8546066&rft.externalDocID=8546066