File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Underline detection and removal in a document image using multiple strategies

TitleUnderline detection and removal in a document image using multiple strategies
Authors
KeywordsComputers
Artificial intelligence
Issue Date2004
PublisherIEEE, Computer Society.
Citation
The 17th International Conference on Pattern Recognition, Cambridge, UK, 23-26 August 2004, v. 2, p. 578-581 How to Cite?
AbstractThis work presents a novel three-module approach for underline detection and removal in Chinese/English OCR. The detection module uses strategies of connected component analysis and bottom edge analysis. The removal module uses different methods for different kinds of underlines. The disambiguation module is effected via recognition confidence comparison for reducing the risk of removing wrongly doubtful underlines. Our approach can deal with untouched, touched, broken and slightly curved underlines. In a benchmark test using single text line images extracted from UW-I database and images captured by C-Pen, we demonstrate that our approach has little negative effect on pure-text images, and can detect and remove reliably underlines in text line images with underlines.
Persistent Identifierhttp://hdl.handle.net/10722/45524
ISSN

 

DC FieldValueLanguage
dc.contributor.authorBai, Zen_HK
dc.contributor.authorHuo, Qen_HK
dc.date.accessioned2007-10-30T06:28:25Z-
dc.date.available2007-10-30T06:28:25Z-
dc.date.issued2004en_HK
dc.identifier.citationThe 17th International Conference on Pattern Recognition, Cambridge, UK, 23-26 August 2004, v. 2, p. 578-581en_HK
dc.identifier.issn1051-4651en_HK
dc.identifier.urihttp://hdl.handle.net/10722/45524-
dc.description.abstractThis work presents a novel three-module approach for underline detection and removal in Chinese/English OCR. The detection module uses strategies of connected component analysis and bottom edge analysis. The removal module uses different methods for different kinds of underlines. The disambiguation module is effected via recognition confidence comparison for reducing the risk of removing wrongly doubtful underlines. Our approach can deal with untouched, touched, broken and slightly curved underlines. In a benchmark test using single text line images extracted from UW-I database and images captured by C-Pen, we demonstrate that our approach has little negative effect on pure-text images, and can detect and remove reliably underlines in text line images with underlines.en_HK
dc.format.extent318371 bytes-
dc.format.extent7254 bytes-
dc.format.mimetypeapplication/pdf-
dc.format.mimetypetext/plain-
dc.languageengen_HK
dc.publisherIEEE, Computer Society.en_HK
dc.rightsCreative Commons: Attribution 3.0 Hong Kong License-
dc.rights©2004 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.en_HK
dc.subjectComputersen_HK
dc.subjectArtificial intelligenceen_HK
dc.titleUnderline detection and removal in a document image using multiple strategiesen_HK
dc.typeConference_Paperen_HK
dc.identifier.openurlhttp://library.hku.hk:4550/resserv?sid=HKU:IR&issn=1051-4651&volume=2&spage=578&epage=581&date=2004&atitle=Underline+detection+and+removal+in+a+document+image+using+multiple+strategiesen_HK
dc.description.naturepublished_or_final_versionen_HK
dc.identifier.doi10.1109/ICPR.2004.1334314en_HK
dc.identifier.hkuros101970-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats