Character recognition in the presence of occluding clutter
Identifieur interne : 000A91 ( Main/Exploration ); précédent : 000A90; suivant : 000A92Character recognition in the presence of occluding clutter
Auteurs : Knut T. Fosseide [Norvège] ; Lars Aurdal [Norvège]Source :
- Proceedings of SPIE, the International Society for Optical Engineering [ 0277-786X ] ; 2009.
Descripteurs français
- Pascal (Inist)
English descriptors
- KwdEn :
Abstract
Many documents contain (free-hand) underlining, "COPY" stamps, crossed out text, doodling and other "clutter" that occlude the text. In many cases, it is not possible to separate the text from the clutter. Commercial OCR solutions typically fail for cluttered text. We present a new method for finding the clutter using path analysis of points on the skeleton of the clutter/text connected component. This method can separate the clutter from the text even for fairly complex clutter shapes. Even with good localization of occluding clutter, it is difficult to use feature-based recognition for occluded characters, simply because the clutter affects the features in various ways. We propose a new algorithm that uses adapted templates of the font in the document that can be used for all forms of occlusion of the character. The method finds the simulated localization of the corresponding clutter in the templates and compares the unaffected parts of the templates and the character. The method has proved highly successful even when much of the character is occluded. We present examples of clutter localization and character recognition with occluded characters.
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream PascalFrancis, to step Corpus: 000217
- to stream PascalFrancis, to step Curation: 000562
- to stream PascalFrancis, to step Checkpoint: 000208
- to stream Main, to step Merge: 000B02
- to stream Main, to step Curation: 000A91
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Character recognition in the presence of occluding clutter</title><author><name sortKey="Fosseide, Knut T" sort="Fosseide, Knut T" uniqKey="Fosseide K" first="Knut T." last="Fosseide">Knut T. Fosseide</name><affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Lumex AS Ovre Vollgt 7</s1><s2>0158 Oslo</s2><s3>NOR</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ></inist:fA14><country>Norvège</country><wicri:noRegion>Lumex AS Ovre Vollgt 7</wicri:noRegion></affiliation></author><author><name sortKey="Aurdal, Lars" sort="Aurdal, Lars" uniqKey="Aurdal L" first="Lars" last="Aurdal">Lars Aurdal</name><affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Lumex AS Ovre Vollgt 7</s1><s2>0158 Oslo</s2><s3>NOR</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ></inist:fA14><country>Norvège</country><wicri:noRegion>Lumex AS Ovre Vollgt 7</wicri:noRegion></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">INIST</idno><idno type="inist">09-0372238</idno><date when="2009">2009</date><idno type="stanalyst">PASCAL 09-0372238 INIST</idno><idno type="RBID">Pascal:09-0372238</idno><idno type="wicri:Area/PascalFrancis/Corpus">000217</idno><idno type="wicri:Area/PascalFrancis/Curation">000562</idno><idno type="wicri:Area/PascalFrancis/Checkpoint">000208</idno><idno type="wicri:doubleKey">0277-786X:2009:Fosseide K:character:recognition:in</idno><idno type="wicri:Area/Main/Merge">000B02</idno><idno type="wicri:Area/Main/Curation">000A91</idno><idno type="wicri:Area/Main/Exploration">000A91</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Character recognition in the presence of occluding clutter</title><author><name sortKey="Fosseide, Knut T" sort="Fosseide, Knut T" uniqKey="Fosseide K" first="Knut T." last="Fosseide">Knut T. Fosseide</name><affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Lumex AS Ovre Vollgt 7</s1><s2>0158 Oslo</s2><s3>NOR</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ></inist:fA14><country>Norvège</country><wicri:noRegion>Lumex AS Ovre Vollgt 7</wicri:noRegion></affiliation></author><author><name sortKey="Aurdal, Lars" sort="Aurdal, Lars" uniqKey="Aurdal L" first="Lars" last="Aurdal">Lars Aurdal</name><affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Lumex AS Ovre Vollgt 7</s1><s2>0158 Oslo</s2><s3>NOR</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ></inist:fA14><country>Norvège</country><wicri:noRegion>Lumex AS Ovre Vollgt 7</wicri:noRegion></affiliation></author></analytic><series><title level="j" type="main">Proceedings of SPIE, the International Society for Optical Engineering</title><title level="j" type="abbreviated">Proc. SPIE Int. Soc. Opt. Eng.</title><idno type="ISSN">0277-786X</idno><imprint><date when="2009">2009</date></imprint></series></biblStruct></sourceDesc><seriesStmt><title level="j" type="main">Proceedings of SPIE, the International Society for Optical Engineering</title><title level="j" type="abbreviated">Proc. SPIE Int. Soc. Opt. Eng.</title><idno type="ISSN">0277-786X</idno></seriesStmt></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Algorithms</term><term>Character recognition</term><term>Clutter</term><term>Complex shape</term><term>Localization</term><term>Optical character recognition</term><term>Pattern recognition</term><term>Skeleton</term></keywords><keywords scheme="Pascal" xml:lang="fr"><term>Algorithme</term><term>Reconnaissance caractère</term><term>Fouillis écho</term><term>Reconnaissance optique caractère</term><term>Squelette</term><term>Forme complexe</term><term>Localisation</term><term>Reconnaissance forme</term><term>0130C</term><term>Traitement image</term><term>4230V</term><term>4230S</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">Many documents contain (free-hand) underlining, "COPY" stamps, crossed out text, doodling and other "clutter" that occlude the text. In many cases, it is not possible to separate the text from the clutter. Commercial OCR solutions typically fail for cluttered text. We present a new method for finding the clutter using path analysis of points on the skeleton of the clutter/text connected component. This method can separate the clutter from the text even for fairly complex clutter shapes. Even with good localization of occluding clutter, it is difficult to use feature-based recognition for occluded characters, simply because the clutter affects the features in various ways. We propose a new algorithm that uses adapted templates of the font in the document that can be used for all forms of occlusion of the character. The method finds the simulated localization of the corresponding clutter in the templates and compares the unaffected parts of the templates and the character. The method has proved highly successful even when much of the character is occluded. We present examples of clutter localization and character recognition with occluded characters.</div></front></TEI><affiliations><list><country><li>Norvège</li></country></list><tree><country name="Norvège"><noRegion><name sortKey="Fosseide, Knut T" sort="Fosseide, Knut T" uniqKey="Fosseide K" first="Knut T." last="Fosseide">Knut T. Fosseide</name></noRegion><name sortKey="Aurdal, Lars" sort="Aurdal, Lars" uniqKey="Aurdal L" first="Lars" last="Aurdal">Lars Aurdal</name></country></tree></affiliations></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000A91 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000A91 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Ticri/CIDE
|area= OcrV1
|flux= Main
|étape= Exploration
|type= RBID
|clé= Pascal:09-0372238
|texte= Character recognition in the presence of occluding clutter
}}
| This area was generated with Dilib version V0.6.32. |  |