Serveur d'exploration sur l'OCR

Attention, ce site est en cours de développement !
Attention, site généré par des moyens informatiques à partir de corpus bruts.
Les informations ne sont donc pas validées.

Separation algorithm of superimposed pattern using directional decomposition of an image

Identifieur interne : 001772 ( Main/Exploration ); précédent : 001771; suivant : 001773

Separation algorithm of superimposed pattern using directional decomposition of an image

Auteurs : Misako Suwa [Japon] ; Satoshi Naoi [Japon]

Source :

RBID : Pascal:03-0420814

Descripteurs français

English descriptors

Abstract

To recognize a handwritten check mark on a pre-printed character with OCR (Optical Character Recognition), we need to separate the pre-print and the superimposed check mark. By the previous method, an unmarked form image and marked one are matched and overlapping part is removed. Then the remaining pattern is regarded as a superimposed mark pattern. Therefore when the mark pattern and the pre-print is overlapped, the overlapping part is removed with the pre-print. It sometimes causes a decision error of the existence of the check mark. In this paper, we propose a new method to separate a superimposed pattern to preprints using directional decomposition of an image for precise recognition of the check mark.


Affiliations:


Links toward previous steps (curation, corpus...)


Le document en format XML

<record>
<TEI>
<teiHeader>
<fileDesc>
<titleStmt>
<title xml:lang="en" level="a">Separation algorithm of superimposed pattern using directional decomposition of an image</title>
<author>
<name sortKey="Suwa, Misako" sort="Suwa, Misako" uniqKey="Suwa M" first="Misako" last="Suwa">Misako Suwa</name>
<affiliation wicri:level="1">
<inist:fA14 i1="01">
<s1>Fujitsu Laboratories Ltd., 4-1-1, Kamikodanaka, Nakahara-ku</s1>
<s2>Kawasaki-shi, Kanagawa-ken, 211-8588</s2>
<s3>JPN</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>Japon</country>
<wicri:noRegion>Kawasaki-shi, Kanagawa-ken, 211-8588</wicri:noRegion>
</affiliation>
</author>
<author>
<name sortKey="Naoi, Satoshi" sort="Naoi, Satoshi" uniqKey="Naoi S" first="Satoshi" last="Naoi">Satoshi Naoi</name>
<affiliation wicri:level="1">
<inist:fA14 i1="01">
<s1>Fujitsu Laboratories Ltd., 4-1-1, Kamikodanaka, Nakahara-ku</s1>
<s2>Kawasaki-shi, Kanagawa-ken, 211-8588</s2>
<s3>JPN</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>Japon</country>
<wicri:noRegion>Kawasaki-shi, Kanagawa-ken, 211-8588</wicri:noRegion>
</affiliation>
</author>
</titleStmt>
<publicationStmt>
<idno type="wicri:source">INIST</idno>
<idno type="inist">03-0420814</idno>
<date when="2003">2003</date>
<idno type="stanalyst">PASCAL 03-0420814 INIST</idno>
<idno type="RBID">Pascal:03-0420814</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000601</idno>
<idno type="wicri:Area/PascalFrancis/Curation">000190</idno>
<idno type="wicri:Area/PascalFrancis/Checkpoint">000536</idno>
<idno type="wicri:doubleKey">1017-2653:2003:Suwa M:separation:algorithm:of</idno>
<idno type="wicri:Area/Main/Merge">001850</idno>
<idno type="wicri:Area/Main/Curation">001772</idno>
<idno type="wicri:Area/Main/Exploration">001772</idno>
</publicationStmt>
<sourceDesc>
<biblStruct>
<analytic>
<title xml:lang="en" level="a">Separation algorithm of superimposed pattern using directional decomposition of an image</title>
<author>
<name sortKey="Suwa, Misako" sort="Suwa, Misako" uniqKey="Suwa M" first="Misako" last="Suwa">Misako Suwa</name>
<affiliation wicri:level="1">
<inist:fA14 i1="01">
<s1>Fujitsu Laboratories Ltd., 4-1-1, Kamikodanaka, Nakahara-ku</s1>
<s2>Kawasaki-shi, Kanagawa-ken, 211-8588</s2>
<s3>JPN</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>Japon</country>
<wicri:noRegion>Kawasaki-shi, Kanagawa-ken, 211-8588</wicri:noRegion>
</affiliation>
</author>
<author>
<name sortKey="Naoi, Satoshi" sort="Naoi, Satoshi" uniqKey="Naoi S" first="Satoshi" last="Naoi">Satoshi Naoi</name>
<affiliation wicri:level="1">
<inist:fA14 i1="01">
<s1>Fujitsu Laboratories Ltd., 4-1-1, Kamikodanaka, Nakahara-ku</s1>
<s2>Kawasaki-shi, Kanagawa-ken, 211-8588</s2>
<s3>JPN</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>Japon</country>
<wicri:noRegion>Kawasaki-shi, Kanagawa-ken, 211-8588</wicri:noRegion>
</affiliation>
</author>
</analytic>
<series>
<title level="j" type="main">SPIE proceedings series</title>
<idno type="ISSN">1017-2653</idno>
<imprint>
<date when="2003">2003</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt>
<title level="j" type="main">SPIE proceedings series</title>
<idno type="ISSN">1017-2653</idno>
</seriesStmt>
</fileDesc>
<profileDesc>
<textClass>
<keywords scheme="KwdEn" xml:lang="en">
<term>Algorithm</term>
<term>Decomposition</term>
<term>Image</term>
<term>Line segment</term>
<term>Manuscript character</term>
<term>Optical character recognition</term>
<term>Overlap</term>
<term>Printed document</term>
<term>Separation</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr">
<term>Reconnaissance optique caractère</term>
<term>Image</term>
<term>Document imprimé</term>
<term>Caractère manuscrit</term>
<term>Chevauchement</term>
<term>Décomposition</term>
<term>Segment droite</term>
<term>Séparation</term>
<term>Algorithme</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front>
<div type="abstract" xml:lang="en">To recognize a handwritten check mark on a pre-printed character with OCR (Optical Character Recognition), we need to separate the pre-print and the superimposed check mark. By the previous method, an unmarked form image and marked one are matched and overlapping part is removed. Then the remaining pattern is regarded as a superimposed mark pattern. Therefore when the mark pattern and the pre-print is overlapped, the overlapping part is removed with the pre-print. It sometimes causes a decision error of the existence of the check mark. In this paper, we propose a new method to separate a superimposed pattern to preprints using directional decomposition of an image for precise recognition of the check mark.</div>
</front>
</TEI>
<affiliations>
<list>
<country>
<li>Japon</li>
</country>
</list>
<tree>
<country name="Japon">
<noRegion>
<name sortKey="Suwa, Misako" sort="Suwa, Misako" uniqKey="Suwa M" first="Misako" last="Suwa">Misako Suwa</name>
</noRegion>
<name sortKey="Naoi, Satoshi" sort="Naoi, Satoshi" uniqKey="Naoi S" first="Satoshi" last="Naoi">Satoshi Naoi</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 001772 | SxmlIndent | more

Ou

HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 001772 | 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:03-0420814
   |texte=   Separation algorithm of superimposed pattern using directional decomposition of an image
}}

Wicri

This area was generated with Dilib version V0.6.32.
Data generation: Sat Nov 11 16:53:45 2017. Site generation: Mon Mar 11 23:15:16 2024