File Download
Supplementary
-
Citations:
- Appears in Collections:
Conference Paper: Underline detection and removal in a document image using multiple strategies
Title | Underline detection and removal in a document image using multiple strategies |
---|---|
Authors | |
Keywords | Computers Artificial intelligence |
Issue Date | 2004 |
Publisher | IEEE, Computer Society. |
Citation | The 17th International Conference on Pattern Recognition, Cambridge, UK, 23-26 August 2004, v. 2, p. 578-581 How to Cite? |
Abstract | This 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 Identifier | http://hdl.handle.net/10722/45524 |
ISSN | 2023 SCImago Journal Rankings: 0.584 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Bai, Z | en_HK |
dc.contributor.author | Huo, Q | en_HK |
dc.date.accessioned | 2007-10-30T06:28:25Z | - |
dc.date.available | 2007-10-30T06:28:25Z | - |
dc.date.issued | 2004 | en_HK |
dc.identifier.citation | The 17th International Conference on Pattern Recognition, Cambridge, UK, 23-26 August 2004, v. 2, p. 578-581 | en_HK |
dc.identifier.issn | 1051-4651 | en_HK |
dc.identifier.uri | http://hdl.handle.net/10722/45524 | - |
dc.description.abstract | This 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.extent | 318371 bytes | - |
dc.format.extent | 7254 bytes | - |
dc.format.mimetype | application/pdf | - |
dc.format.mimetype | text/plain | - |
dc.language | eng | en_HK |
dc.publisher | IEEE, Computer Society. | en_HK |
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. | - |
dc.subject | Computers | en_HK |
dc.subject | Artificial intelligence | en_HK |
dc.title | Underline detection and removal in a document image using multiple strategies | en_HK |
dc.type | Conference_Paper | en_HK |
dc.identifier.openurl | http://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+strategies | en_HK |
dc.description.nature | published_or_final_version | en_HK |
dc.identifier.doi | 10.1109/ICPR.2004.1334314 | en_HK |
dc.identifier.hkuros | 101970 | - |
dc.identifier.issnl | 1051-4651 | - |