A character recognition system with learning dictionary for handwritten drawings
Identifieur interne : 000664 ( Istex/Corpus ); précédent : 000663; suivant : 000665A character recognition system with learning dictionary for handwritten drawings
Auteurs : Mitsuo Ishii ; Michiko Iwasaki ; Masahiro YamadaSource :
- Systems and Computers in Japan [ 0882-1666 ] ; 1987.
Abstract
This paper discusses the character recognition system used in the automatic input of drawings. The character considered is of small size, 2 to 5 mm, which is sampled with a low resolution such as 5 lines/mm. The recognition is performed by a kind of pattern matching. The input pattern is superposed on the dictionary pattern. The distance distortion measure is introduced which represents the degree of mismatch with the closest pixels as the corresponding pair. To reflect the structural feature of the character, the weighted distortion measure is proposed which considers the environment of the corresponding pixels. By this elaboration, the misrecognition rate was decreased by 45 percent. To cope with the problem arising from representing the two‐dimensional pattern distortion by a single number, dictionary patterns are increased. The generation and the structure of the dictionary are discussed. A hierarchical dictionary with learning pointer is constructed which records the mistakes made in the course of training. The feature of the method is that mistakes made in the past can be utilized and the processing time does not increase so rapidly in proportion to the number of dictionary patterns. Approximately 30,000 characters were learned, and the practical recognition performance was verified through the recognition experiment for the drawings.
Url:
DOI: 10.1002/scj.4690180207
Links to Exploration step
ISTEX:EEE90BA43BE55BE2256DA874CDAD5923CF95AA9ALe document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">A character recognition system with learning dictionary for handwritten drawings</title><author><name sortKey="Ishii, Mitsuo" sort="Ishii, Mitsuo" uniqKey="Ishii M" first="Mitsuo" last="Ishii">Mitsuo Ishii</name><affiliation><mods:affiliation>Fujitsu Laboratories Ltd., Kawasaki, Japan 211</mods:affiliation></affiliation></author><author><name sortKey="Iwasaki, Michiko" sort="Iwasaki, Michiko" uniqKey="Iwasaki M" first="Michiko" last="Iwasaki">Michiko Iwasaki</name><affiliation><mods:affiliation>Fujitsu Laboratories Ltd., Kawasaki, Japan 211</mods:affiliation></affiliation></author><author><name sortKey="Yamada, Masahiro" sort="Yamada, Masahiro" uniqKey="Yamada M" first="Masahiro" last="Yamada">Masahiro Yamada</name><affiliation><mods:affiliation>Fujitsu Social Science Laboratories Ltd., Tokyo, Japan 105</mods:affiliation></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:EEE90BA43BE55BE2256DA874CDAD5923CF95AA9A</idno><date when="1987" year="1987">1987</date><idno type="doi">10.1002/scj.4690180207</idno><idno type="url">https://api.istex.fr/document/EEE90BA43BE55BE2256DA874CDAD5923CF95AA9A/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">000664</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">A character recognition system with learning dictionary for handwritten drawings</title><author><name sortKey="Ishii, Mitsuo" sort="Ishii, Mitsuo" uniqKey="Ishii M" first="Mitsuo" last="Ishii">Mitsuo Ishii</name><affiliation><mods:affiliation>Fujitsu Laboratories Ltd., Kawasaki, Japan 211</mods:affiliation></affiliation></author><author><name sortKey="Iwasaki, Michiko" sort="Iwasaki, Michiko" uniqKey="Iwasaki M" first="Michiko" last="Iwasaki">Michiko Iwasaki</name><affiliation><mods:affiliation>Fujitsu Laboratories Ltd., Kawasaki, Japan 211</mods:affiliation></affiliation></author><author><name sortKey="Yamada, Masahiro" sort="Yamada, Masahiro" uniqKey="Yamada M" first="Masahiro" last="Yamada">Masahiro Yamada</name><affiliation><mods:affiliation>Fujitsu Social Science Laboratories Ltd., Tokyo, Japan 105</mods:affiliation></affiliation></author></analytic><monogr></monogr><series><title level="j">Systems and Computers in Japan</title><title level="j" type="abbrev">Syst. Comp. Jpn.</title><idno type="ISSN">0882-1666</idno><idno type="eISSN">1520-684X</idno><imprint><publisher>Wiley Subscription Services, Inc., A Wiley Company</publisher><pubPlace>New York</pubPlace><date type="published" when="1987">1987</date><biblScope unit="volume">18</biblScope><biblScope unit="issue">2</biblScope><biblScope unit="page" from="65">65</biblScope><biblScope unit="page" to="76">76</biblScope></imprint><idno type="ISSN">0882-1666</idno></series><idno type="istex">EEE90BA43BE55BE2256DA874CDAD5923CF95AA9A</idno><idno type="DOI">10.1002/scj.4690180207</idno><idno type="ArticleID">SCJ4690180207</idno></biblStruct></sourceDesc><seriesStmt><idno type="ISSN">0882-1666</idno></seriesStmt></fileDesc><profileDesc><textClass></textClass><langUsage><language ident="en">en</language></langUsage></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">This paper discusses the character recognition system used in the automatic input of drawings. The character considered is of small size, 2 to 5 mm, which is sampled with a low resolution such as 5 lines/mm. The recognition is performed by a kind of pattern matching. The input pattern is superposed on the dictionary pattern. The distance distortion measure is introduced which represents the degree of mismatch with the closest pixels as the corresponding pair. To reflect the structural feature of the character, the weighted distortion measure is proposed which considers the environment of the corresponding pixels. By this elaboration, the misrecognition rate was decreased by 45 percent. To cope with the problem arising from representing the two‐dimensional pattern distortion by a single number, dictionary patterns are increased. The generation and the structure of the dictionary are discussed. A hierarchical dictionary with learning pointer is constructed which records the mistakes made in the course of training. The feature of the method is that mistakes made in the past can be utilized and the processing time does not increase so rapidly in proportion to the number of dictionary patterns. Approximately 30,000 characters were learned, and the practical recognition performance was verified through the recognition experiment for the drawings.</div></front></TEI><istex><corpusName>wiley</corpusName><author><json:item><name>Mitsuo Ishii</name><affiliations><json:string>Fujitsu Laboratories Ltd., Kawasaki, Japan 211</json:string></affiliations></json:item><json:item><name>Michiko Iwasaki</name><affiliations><json:string>Fujitsu Laboratories Ltd., Kawasaki, Japan 211</json:string></affiliations></json:item><json:item><name>Masahiro Yamada</name><affiliations><json:string>Fujitsu Social Science Laboratories Ltd., Tokyo, Japan 105</json:string></affiliations></json:item></author><articleId><json:string>SCJ4690180207</json:string></articleId><language><json:string>eng</json:string></language><abstract>This paper discusses the character recognition system used in the automatic input of drawings. The character considered is of small size, 2 to 5 mm, which is sampled with a low resolution such as 5 lines/mm. The recognition is performed by a kind of pattern matching. The input pattern is superposed on the dictionary pattern. The distance distortion measure is introduced which represents the degree of mismatch with the closest pixels as the corresponding pair. To reflect the structural feature of the character, the weighted distortion measure is proposed which considers the environment of the corresponding pixels. By this elaboration, the misrecognition rate was decreased by 45 percent. To cope with the problem arising from representing the two‐dimensional pattern distortion by a single number, dictionary patterns are increased. The generation and the structure of the dictionary are discussed. A hierarchical dictionary with learning pointer is constructed which records the mistakes made in the course of training. The feature of the method is that mistakes made in the past can be utilized and the processing time does not increase so rapidly in proportion to the number of dictionary patterns. Approximately 30,000 characters were learned, and the practical recognition performance was verified through the recognition experiment for the drawings.</abstract><qualityIndicators><score>7.262</score><pdfVersion>1.3</pdfVersion><pdfPageSize>594 x 828 pts</pdfPageSize><refBibsNative>true</refBibsNative><keywordCount>0</keywordCount><abstractCharCount>1362</abstractCharCount><pdfWordCount>4778</pdfWordCount><pdfCharCount>26489</pdfCharCount><pdfPageCount>12</pdfPageCount><abstractWordCount>207</abstractWordCount></qualityIndicators><title>A character recognition system with learning dictionary for handwritten drawings</title><genre.original><json:string>article</json:string></genre.original><genre><json:string>article</json:string></genre><host><volume>18</volume><publisherId><json:string>SCJ</json:string></publisherId><pages><total>12</total><last>76</last><first>65</first></pages><issn><json:string>0882-1666</json:string></issn><issue>2</issue><subject><json:item><value>Article</value></json:item></subject><genre><json:string>journal</json:string></genre><language><json:string>unknown</json:string></language><eissn><json:string>1520-684X</json:string></eissn><title>Systems and Computers in Japan</title><doi><json:string>10.1002/(ISSN)1520-684X</json:string></doi></host><publicationDate>1987</publicationDate><copyrightDate>1987</copyrightDate><doi><json:string>10.1002/scj.4690180207</json:string></doi><id>EEE90BA43BE55BE2256DA874CDAD5923CF95AA9A</id><fulltext><json:item><original>true</original><mimetype>application/pdf</mimetype><extension>pdf</extension><uri>https://api.istex.fr/document/EEE90BA43BE55BE2256DA874CDAD5923CF95AA9A/fulltext/pdf</uri></json:item><json:item><original>false</original><mimetype>application/zip</mimetype><extension>zip</extension><uri>https://api.istex.fr/document/EEE90BA43BE55BE2256DA874CDAD5923CF95AA9A/fulltext/zip</uri></json:item><istex:fulltextTEI uri="https://api.istex.fr/document/EEE90BA43BE55BE2256DA874CDAD5923CF95AA9A/fulltext/tei"><teiHeader><fileDesc><titleStmt><title level="a" type="main" xml:lang="en">A character recognition system with learning dictionary for handwritten drawings</title></titleStmt><publicationStmt><authority>ISTEX</authority><publisher>Wiley Subscription Services, Inc., A Wiley Company</publisher><pubPlace>New York</pubPlace><availability><p>WILEY</p></availability><date>1987</date></publicationStmt><sourceDesc><biblStruct type="inbook"><analytic><title level="a" type="main" xml:lang="en">A character recognition system with learning dictionary for handwritten drawings</title><author><persName><forename type="first">Mitsuo</forename><surname>Ishii</surname></persName><note type="biography">Mitsuo Ishii. Graduated 1966 Dept. Electrical Eng., Fac. Eng., Nagoya Inst. Technology. Completed Master's program 1968 Grad. School, Tokyo Inst. Tech., and affiliated with Fujitsu Lab. Presently, Deputy Director, System Res. Div. Engaged in research and development in signal processing for image communication, diagram input, CAD system and computer graphics. Member, Inf. Proc. SOC. Jap., TV SOC. Jap., and I.E.E.E.</note><affiliation>Mitsuo Ishii. Graduated 1966 Dept. Electrical Eng., Fac. Eng., Nagoya Inst. Technology. Completed Master's program 1968 Grad. School, Tokyo Inst. Tech., and affiliated with Fujitsu Lab. Presently, Deputy Director, System Res. Div. Engaged in research and development in signal processing for image communication, diagram input, CAD system and computer graphics. Member, Inf. Proc. SOC. Jap., TV SOC. Jap., and I.E.E.E.</affiliation><affiliation>Fujitsu Laboratories Ltd., Kawasaki, Japan 211</affiliation></author><author><persName><forename type="first">Michiko</forename><surname>Iwasaki</surname></persName><note type="biography">Michiko Iwasaki. Graduated 1973 Dept. Electronics and Comm. Eng., Fac. Eng., Musashi Inst. Technology and affiliated with Fujitsu Lab. Presently engaged in research in diagram input in Pattern Res. Division.</note><affiliation>Michiko Iwasaki. Graduated 1973 Dept. Electronics and Comm. Eng., Fac. Eng., Musashi Inst. Technology and affiliated with Fujitsu Lab. Presently engaged in research in diagram input in Pattern Res. Division.</affiliation><affiliation>Fujitsu Laboratories Ltd., Kawasaki, Japan 211</affiliation></author><author><persName><forename type="first">Masahiro</forename><surname>Yamada</surname></persName><note type="biography">Masahiro Yamada. Graduated 1980 Dept. Phys., Fac. Sci., Chiba Univ., and affiliated with Fujitsu Social Science Lab.</note><affiliation>Masahiro Yamada. Graduated 1980 Dept. Phys., Fac. Sci., Chiba Univ., and affiliated with Fujitsu Social Science Lab.</affiliation><affiliation>Fujitsu Social Science Laboratories Ltd., Tokyo, Japan 105</affiliation></author></analytic><monogr><title level="j">Systems and Computers in Japan</title><title level="j" type="abbrev">Syst. Comp. Jpn.</title><idno type="pISSN">0882-1666</idno><idno type="eISSN">1520-684X</idno><idno type="DOI">10.1002/(ISSN)1520-684X</idno><imprint><publisher>Wiley Subscription Services, Inc., A Wiley Company</publisher><pubPlace>New York</pubPlace><date type="published" when="1987"></date><biblScope unit="volume">18</biblScope><biblScope unit="issue">2</biblScope><biblScope unit="page" from="65">65</biblScope><biblScope unit="page" to="76">76</biblScope></imprint></monogr><idno type="istex">EEE90BA43BE55BE2256DA874CDAD5923CF95AA9A</idno><idno type="DOI">10.1002/scj.4690180207</idno><idno type="ArticleID">SCJ4690180207</idno></biblStruct></sourceDesc></fileDesc><profileDesc><creation><date>1987</date></creation><langUsage><language ident="en">en</language></langUsage><abstract xml:lang="en"><p>This paper discusses the character recognition system used in the automatic input of drawings. The character considered is of small size, 2 to 5 mm, which is sampled with a low resolution such as 5 lines/mm. The recognition is performed by a kind of pattern matching. The input pattern is superposed on the dictionary pattern. The distance distortion measure is introduced which represents the degree of mismatch with the closest pixels as the corresponding pair. To reflect the structural feature of the character, the weighted distortion measure is proposed which considers the environment of the corresponding pixels. By this elaboration, the misrecognition rate was decreased by 45 percent. To cope with the problem arising from representing the two‐dimensional pattern distortion by a single number, dictionary patterns are increased. The generation and the structure of the dictionary are discussed. A hierarchical dictionary with learning pointer is constructed which records the mistakes made in the course of training. The feature of the method is that mistakes made in the past can be utilized and the processing time does not increase so rapidly in proportion to the number of dictionary patterns. Approximately 30,000 characters were learned, and the practical recognition performance was verified through the recognition experiment for the drawings.</p></abstract><textClass><keywords scheme="Journal Subject"><list><head>article-category</head><item><term>Article</term></item></list></keywords></textClass></profileDesc><revisionDesc><change when="1987">Published</change></revisionDesc></teiHeader></istex:fulltextTEI><json:item><original>false</original><mimetype>text/plain</mimetype><extension>txt</extension><uri>https://api.istex.fr/document/EEE90BA43BE55BE2256DA874CDAD5923CF95AA9A/fulltext/txt</uri></json:item></fulltext><metadata><istex:metadataXml wicri:clean="Wiley, elements deleted: body"><istex:xmlDeclaration>version="1.0" encoding="UTF-8" standalone="yes"</istex:xmlDeclaration><istex:document><component version="2.0" type="serialArticle" xml:lang="en"><header><publicationMeta level="product"><publisherInfo><publisherName>Wiley Subscription Services, Inc., A Wiley Company</publisherName><publisherLoc>New York</publisherLoc></publisherInfo><doi registered="yes">10.1002/(ISSN)1520-684X</doi><issn type="print">0882-1666</issn><issn type="electronic">1520-684X</issn><idGroup><id type="product" value="SCJ"></id></idGroup><titleGroup><title type="main" xml:lang="en" sort="SYSTEMS AND COMPUTERS IN JAPAN">Systems and Computers in Japan</title><title type="short">Syst. Comp. Jpn.</title></titleGroup></publicationMeta><publicationMeta level="part" position="20"><doi origin="wiley" registered="yes">10.1002/scj.v18:2</doi><numberingGroup><numbering type="journalVolume" number="18">18</numbering><numbering type="journalIssue">2</numbering></numberingGroup><coverDate startDate="1987">1987</coverDate></publicationMeta><publicationMeta level="unit" type="article" position="7" status="forIssue"><doi origin="wiley" registered="yes">10.1002/scj.4690180207</doi><idGroup><id type="unit" value="SCJ4690180207"></id></idGroup><countGroup><count type="pageTotal" number="12"></count></countGroup><titleGroup><title type="articleCategory">Article</title><title type="tocHeading1">Articles</title></titleGroup><copyright ownership="publisher">Copyright © 1987 Wiley Periodicals, Inc., A Wiley Company</copyright><eventGroup><event type="firstOnline" date="2007-03-21"></event><event type="publishedOnlineFinalForm" date="2007-03-21"></event><event type="xmlConverted" agent="Converter:JWSART34_TO_WML3G version:2.3.2 mode:FullText source:HeaderRef result:HeaderRef" date="2010-03-04"></event><event type="xmlConverted" agent="Converter:WILEY_ML3G_TO_WILEY_ML3GV2 version:3.8.8" date="2014-02-08"></event><event type="xmlConverted" agent="Converter:WML3G_To_WML3G version:4.1.7 mode:FullText,remove_FC" date="2014-11-04"></event></eventGroup><numberingGroup><numbering type="pageFirst">65</numbering><numbering type="pageLast">76</numbering></numberingGroup><linkGroup><link type="toTypesetVersion" href="file:SCJ.SCJ4690180207.pdf"></link></linkGroup></publicationMeta><contentMeta><countGroup><count type="figureTotal" number="10"></count><count type="tableTotal" number="4"></count><count type="referenceTotal" number="12"></count></countGroup><titleGroup><title type="main" xml:lang="en">A character recognition system with learning dictionary for handwritten drawings</title><title type="short" xml:lang="en">A character recognition system with learning dictionary for handwritten drawings</title></titleGroup><creators><creator xml:id="au1" creatorRole="author" affiliationRef="#af1" noteRef="#fn1"><personName><givenNames>Mitsuo</givenNames><familyName>Ishii</familyName></personName></creator><creator xml:id="au2" creatorRole="author" affiliationRef="#af1" noteRef="#fn2"><personName><givenNames>Michiko</givenNames><familyName>Iwasaki</familyName></personName></creator><creator xml:id="au3" creatorRole="author" affiliationRef="#af2" noteRef="#fn3"><personName><givenNames>Masahiro</givenNames><familyName>Yamada</familyName></personName></creator></creators><affiliationGroup><affiliation xml:id="af1" countryCode="JP" type="organization"><unparsedAffiliation>Fujitsu Laboratories Ltd., Kawasaki, Japan 211</unparsedAffiliation></affiliation><affiliation xml:id="af2" countryCode="JP" type="organization"><unparsedAffiliation>Fujitsu Social Science Laboratories Ltd., Tokyo, Japan 105</unparsedAffiliation></affiliation></affiliationGroup><abstractGroup><abstract type="main" xml:lang="en"><title type="main">Abstract</title><p>This paper discusses the character recognition system used in the automatic input of drawings. The character considered is of small size, 2 to 5 mm, which is sampled with a low resolution such as 5 lines/mm. The recognition is performed by a kind of pattern matching. The input pattern is superposed on the dictionary pattern. The distance distortion measure is introduced which represents the degree of mismatch with the closest pixels as the corresponding pair. To reflect the structural feature of the character, the weighted distortion measure is proposed which considers the environment of the corresponding pixels. By this elaboration, the misrecognition rate was decreased by 45 percent. To cope with the problem arising from representing the two‐dimensional pattern distortion by a single number, dictionary patterns are increased. The generation and the structure of the dictionary are discussed. A hierarchical dictionary with learning pointer is constructed which records the mistakes made in the course of training. The feature of the method is that mistakes made in the past can be utilized and the processing time does not increase so rapidly in proportion to the number of dictionary patterns. Approximately 30,000 characters were learned, and the practical recognition performance was verified through the recognition experiment for the drawings.</p></abstract></abstractGroup></contentMeta><noteGroup><note xml:id="fn1"><p>Mitsuo Ishii. Graduated 1966 Dept. Electrical Eng., Fac. Eng., Nagoya Inst. Technology. Completed Master's program 1968 Grad. School, Tokyo Inst. Tech., and affiliated with Fujitsu Lab. Presently, Deputy Director, System Res. Div. Engaged in research and development in signal processing for image communication, diagram input, CAD system and computer graphics. Member, Inf. Proc. SOC. Jap., TV SOC. Jap., and I.E.E.E.</p></note><note xml:id="fn2"><p>Michiko Iwasaki. Graduated 1973 Dept. Electronics and Comm. Eng., Fac. Eng., Musashi Inst. Technology and affiliated with Fujitsu Lab. Presently engaged in research in diagram input in Pattern Res. Division.</p></note><note xml:id="fn3"><p>Masahiro Yamada. Graduated 1980 Dept. Phys., Fac. Sci., Chiba Univ., and affiliated with Fujitsu Social Science Lab.</p></note></noteGroup></header></component></istex:document></istex:metadataXml><mods version="3.6"><titleInfo lang="en"><title>A character recognition system with learning dictionary for handwritten drawings</title></titleInfo><titleInfo type="abbreviated" lang="en"><title>A character recognition system with learning dictionary for handwritten drawings</title></titleInfo><titleInfo type="alternative" contentType="CDATA" lang="en"><title>A character recognition system with learning dictionary for handwritten drawings</title></titleInfo><name type="personal"><namePart type="given">Mitsuo</namePart><namePart type="family">Ishii</namePart><affiliation>Fujitsu Laboratories Ltd., Kawasaki, Japan 211</affiliation><description>Mitsuo Ishii. Graduated 1966 Dept. Electrical Eng., Fac. Eng., Nagoya Inst. Technology. Completed Master's program 1968 Grad. School, Tokyo Inst. Tech., and affiliated with Fujitsu Lab. Presently, Deputy Director, System Res. Div. Engaged in research and development in signal processing for image communication, diagram input, CAD system and computer graphics. Member, Inf. Proc. SOC. Jap., TV SOC. Jap., and I.E.E.E.</description><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">Michiko</namePart><namePart type="family">Iwasaki</namePart><affiliation>Fujitsu Laboratories Ltd., Kawasaki, Japan 211</affiliation><description>Michiko Iwasaki. Graduated 1973 Dept. Electronics and Comm. Eng., Fac. Eng., Musashi Inst. Technology and affiliated with Fujitsu Lab. Presently engaged in research in diagram input in Pattern Res. Division.</description><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">Masahiro</namePart><namePart type="family">Yamada</namePart><affiliation>Fujitsu Social Science Laboratories Ltd., Tokyo, Japan 105</affiliation><description>Masahiro Yamada. Graduated 1980 Dept. Phys., Fac. Sci., Chiba Univ., and affiliated with Fujitsu Social Science Lab.</description><role><roleTerm type="text">author</roleTerm></role></name><typeOfResource>text</typeOfResource><genre type="article" displayLabel="article"></genre><originInfo><publisher>Wiley Subscription Services, Inc., A Wiley Company</publisher><place><placeTerm type="text">New York</placeTerm></place><dateIssued encoding="w3cdtf">1987</dateIssued><copyrightDate encoding="w3cdtf">1987</copyrightDate></originInfo><language><languageTerm type="code" authority="rfc3066">en</languageTerm><languageTerm type="code" authority="iso639-2b">eng</languageTerm></language><physicalDescription><internetMediaType>text/html</internetMediaType><extent unit="figures">10</extent><extent unit="tables">4</extent><extent unit="references">12</extent></physicalDescription><abstract lang="en">This paper discusses the character recognition system used in the automatic input of drawings. The character considered is of small size, 2 to 5 mm, which is sampled with a low resolution such as 5 lines/mm. The recognition is performed by a kind of pattern matching. The input pattern is superposed on the dictionary pattern. The distance distortion measure is introduced which represents the degree of mismatch with the closest pixels as the corresponding pair. To reflect the structural feature of the character, the weighted distortion measure is proposed which considers the environment of the corresponding pixels. By this elaboration, the misrecognition rate was decreased by 45 percent. To cope with the problem arising from representing the two‐dimensional pattern distortion by a single number, dictionary patterns are increased. The generation and the structure of the dictionary are discussed. A hierarchical dictionary with learning pointer is constructed which records the mistakes made in the course of training. The feature of the method is that mistakes made in the past can be utilized and the processing time does not increase so rapidly in proportion to the number of dictionary patterns. Approximately 30,000 characters were learned, and the practical recognition performance was verified through the recognition experiment for the drawings.</abstract><relatedItem type="host"><titleInfo><title>Systems and Computers in Japan</title></titleInfo><titleInfo type="abbreviated"><title>Syst. Comp. Jpn.</title></titleInfo><genre type="journal">journal</genre><subject><genre>article-category</genre><topic>Article</topic></subject><identifier type="ISSN">0882-1666</identifier><identifier type="eISSN">1520-684X</identifier><identifier type="DOI">10.1002/(ISSN)1520-684X</identifier><identifier type="PublisherID">SCJ</identifier><part><date>1987</date><detail type="volume"><caption>vol.</caption><number>18</number></detail><detail type="issue"><caption>no.</caption><number>2</number></detail><extent unit="pages"><start>65</start><end>76</end><total>12</total></extent></part></relatedItem><identifier type="istex">EEE90BA43BE55BE2256DA874CDAD5923CF95AA9A</identifier><identifier type="DOI">10.1002/scj.4690180207</identifier><identifier type="ArticleID">SCJ4690180207</identifier><accessCondition type="use and reproduction" contentType="copyright">Copyright © 1987 Wiley Periodicals, Inc., A Wiley Company</accessCondition><recordInfo><recordContentSource>WILEY</recordContentSource><recordOrigin>Wiley Subscription Services, Inc., A Wiley Company</recordOrigin></recordInfo></mods></metadata><serie></serie></istex></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/Istex/Corpus
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000664 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Istex/Corpus/biblio.hfd -nk 000664 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Ticri/CIDE
|area= OcrV1
|flux= Istex
|étape= Corpus
|type= RBID
|clé= ISTEX:EEE90BA43BE55BE2256DA874CDAD5923CF95AA9A
|texte= A character recognition system with learning dictionary for handwritten drawings
}}
| This area was generated with Dilib version V0.6.32. |  |