A background-thinning-based approach for separating and recognizing connected handwritten digit strings
Identifieur interne : 000B44 ( Istex/Corpus ); précédent : 000B43; suivant : 000B45A background-thinning-based approach for separating and recognizing connected handwritten digit strings
Auteurs : Zhongkang Lu ; Zheru Chi ; Wan-Chi Siu ; Pengfei ShiSource :
- Pattern Recognition [ 0031-3203 ] ; 1997.
Abstract
Most algorithms for segmenting connected handwritten digit strings are based on the analysis of the foreground pixel distributions and the features on the upper/lower contours of the image. In this paper, a new approach is presented to segment connected handwritten two-digit strings based on the thinning of background regions. The algorithm first locates several feature points on the background skeleton of a digit image. Possible segmentation paths are then constructed by matching these feature points. With geometric property measures, all the possible segmentation paths are ranked using fuzzy rules generated from a decision-tree approach. Finally, the top ranked segmentation paths are tested one by one by an optimized nearest neighbor classifier until one of these candidates is accepted based on an acceptance criterion. Experimental results on NIST special database 3 show that our approach can achieve a correct classification rate of 92.5% with only 4.7% of digit strings rejected, which compares favorably with the other techniques tested.
Url:
DOI: 10.1016/S0031-3203(98)00123-X
Links to Exploration step
ISTEX:639BFA6F63CEE00F51A5955B7B0D00F37C5430FELe document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title>A background-thinning-based approach for separating and recognizing connected handwritten digit strings</title><author><name sortKey="Lu, Zhongkang" sort="Lu, Zhongkang" uniqKey="Lu Z" first="Zhongkang" last="Lu">Zhongkang Lu</name><affiliation><mods:affiliation>Department of Electronic Engineering, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong</mods:affiliation></affiliation></author><author><name sortKey="Chi, Zheru" sort="Chi, Zheru" uniqKey="Chi Z" first="Zheru" last="Chi">Zheru Chi</name><affiliation><mods:affiliation>Department of Electronic Engineering, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong</mods:affiliation></affiliation></author><author><name sortKey="Siu, Wan Chi" sort="Siu, Wan Chi" uniqKey="Siu W" first="Wan-Chi" last="Siu">Wan-Chi Siu</name><affiliation><mods:affiliation>Department of Electronic Engineering, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong</mods:affiliation></affiliation></author><author><name sortKey="Shi, Pengfei" sort="Shi, Pengfei" uniqKey="Shi P" first="Pengfei" last="Shi">Pengfei Shi</name><affiliation><mods:affiliation>Institute of Pattern Recognition & Image Processing, Shanghai Jiaotong University, Shanghai 200030, People's Republic of China</mods:affiliation></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:639BFA6F63CEE00F51A5955B7B0D00F37C5430FE</idno><date when="1999" year="1999">1999</date><idno type="doi">10.1016/S0031-3203(98)00123-X</idno><idno type="url">https://api.istex.fr/document/639BFA6F63CEE00F51A5955B7B0D00F37C5430FE/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">000B44</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a">A background-thinning-based approach for separating and recognizing connected handwritten digit strings</title><author><name sortKey="Lu, Zhongkang" sort="Lu, Zhongkang" uniqKey="Lu Z" first="Zhongkang" last="Lu">Zhongkang Lu</name><affiliation><mods:affiliation>Department of Electronic Engineering, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong</mods:affiliation></affiliation></author><author><name sortKey="Chi, Zheru" sort="Chi, Zheru" uniqKey="Chi Z" first="Zheru" last="Chi">Zheru Chi</name><affiliation><mods:affiliation>Department of Electronic Engineering, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong</mods:affiliation></affiliation></author><author><name sortKey="Siu, Wan Chi" sort="Siu, Wan Chi" uniqKey="Siu W" first="Wan-Chi" last="Siu">Wan-Chi Siu</name><affiliation><mods:affiliation>Department of Electronic Engineering, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong</mods:affiliation></affiliation></author><author><name sortKey="Shi, Pengfei" sort="Shi, Pengfei" uniqKey="Shi P" first="Pengfei" last="Shi">Pengfei Shi</name><affiliation><mods:affiliation>Institute of Pattern Recognition & Image Processing, Shanghai Jiaotong University, Shanghai 200030, People's Republic of China</mods:affiliation></affiliation></author></analytic><monogr></monogr><series><title level="j">Pattern Recognition</title><title level="j" type="abbrev">PR</title><idno type="ISSN">0031-3203</idno><imprint><publisher>ELSEVIER</publisher><date type="published" when="1997">1997</date><biblScope unit="volume">32</biblScope><biblScope unit="issue">6</biblScope><biblScope unit="page" from="921">921</biblScope><biblScope unit="page" to="933">933</biblScope></imprint><idno type="ISSN">0031-3203</idno></series><idno type="istex">639BFA6F63CEE00F51A5955B7B0D00F37C5430FE</idno><idno type="DOI">10.1016/S0031-3203(98)00123-X</idno><idno type="PII">S0031-3203(98)00123-X</idno></biblStruct></sourceDesc><seriesStmt><idno type="ISSN">0031-3203</idno></seriesStmt></fileDesc><profileDesc><textClass></textClass><langUsage><language ident="en">en</language></langUsage></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">Most algorithms for segmenting connected handwritten digit strings are based on the analysis of the foreground pixel distributions and the features on the upper/lower contours of the image. In this paper, a new approach is presented to segment connected handwritten two-digit strings based on the thinning of background regions. The algorithm first locates several feature points on the background skeleton of a digit image. Possible segmentation paths are then constructed by matching these feature points. With geometric property measures, all the possible segmentation paths are ranked using fuzzy rules generated from a decision-tree approach. Finally, the top ranked segmentation paths are tested one by one by an optimized nearest neighbor classifier until one of these candidates is accepted based on an acceptance criterion. Experimental results on NIST special database 3 show that our approach can achieve a correct classification rate of 92.5% with only 4.7% of digit strings rejected, which compares favorably with the other techniques tested.</div></front></TEI><istex><corpusName>elsevier</corpusName><author><json:item><name>Zhongkang Lu</name><affiliations><json:string>Department of Electronic Engineering, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong</json:string></affiliations></json:item><json:item><name>Zheru Chi</name><affiliations><json:string>Department of Electronic Engineering, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong</json:string></affiliations></json:item><json:item><name>Wan-Chi Siu</name><affiliations><json:string>Department of Electronic Engineering, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong</json:string></affiliations></json:item><json:item><name>Pengfei Shi</name><affiliations><json:string>Institute of Pattern Recognition & Image Processing, Shanghai Jiaotong University, Shanghai 200030, People's Republic of China</json:string></affiliations></json:item></author><subject><json:item><lang><json:string>eng</json:string></lang><value>Character recognition</value></json:item><json:item><lang><json:string>eng</json:string></lang><value>Character segmentation</value></json:item><json:item><lang><json:string>eng</json:string></lang><value>Connected digit strings</value></json:item><json:item><lang><json:string>eng</json:string></lang><value>Thinning</value></json:item><json:item><lang><json:string>eng</json:string></lang><value>Fuzzy rules</value></json:item></subject><language><json:string>eng</json:string></language><abstract>Most algorithms for segmenting connected handwritten digit strings are based on the analysis of the foreground pixel distributions and the features on the upper/lower contours of the image. In this paper, a new approach is presented to segment connected handwritten two-digit strings based on the thinning of background regions. The algorithm first locates several feature points on the background skeleton of a digit image. Possible segmentation paths are then constructed by matching these feature points. With geometric property measures, all the possible segmentation paths are ranked using fuzzy rules generated from a decision-tree approach. Finally, the top ranked segmentation paths are tested one by one by an optimized nearest neighbor classifier until one of these candidates is accepted based on an acceptance criterion. Experimental results on NIST special database 3 show that our approach can achieve a correct classification rate of 92.5% with only 4.7% of digit strings rejected, which compares favorably with the other techniques tested.</abstract><qualityIndicators><score>6.884</score><pdfVersion>1.2</pdfVersion><pdfPageSize>501 x 713 pts</pdfPageSize><refBibsNative>false</refBibsNative><keywordCount>5</keywordCount><abstractCharCount>1055</abstractCharCount><pdfWordCount>5530</pdfWordCount><pdfCharCount>31279</pdfCharCount><pdfPageCount>13</pdfPageCount><abstractWordCount>157</abstractWordCount></qualityIndicators><title>A background-thinning-based approach for separating and recognizing connected handwritten digit strings</title><pii><json:string>S0031-3203(98)00123-X</json:string></pii><genre><json:string>research-article</json:string></genre><host><volume>32</volume><pii><json:string>S0031-3203(00)X0051-9</json:string></pii><pages><last>933</last><first>921</first></pages><issn><json:string>0031-3203</json:string></issn><issue>6</issue><genre><json:string>Journal</json:string></genre><language><json:string>unknown</json:string></language><title>Pattern Recognition</title><publicationDate>1999</publicationDate></host><categories><wos><json:string>COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE</json:string><json:string>ENGINEERING, ELECTRICAL & ELECTRONIC</json:string></wos></categories><publicationDate>1997</publicationDate><copyrightDate>1999</copyrightDate><doi><json:string>10.1016/S0031-3203(98)00123-X</json:string></doi><id>639BFA6F63CEE00F51A5955B7B0D00F37C5430FE</id><fulltext><json:item><original>true</original><mimetype>application/pdf</mimetype><extension>pdf</extension><uri>https://api.istex.fr/document/639BFA6F63CEE00F51A5955B7B0D00F37C5430FE/fulltext/pdf</uri></json:item><json:item><original>false</original><mimetype>application/zip</mimetype><extension>zip</extension><uri>https://api.istex.fr/document/639BFA6F63CEE00F51A5955B7B0D00F37C5430FE/fulltext/zip</uri></json:item><istex:fulltextTEI uri="https://api.istex.fr/document/639BFA6F63CEE00F51A5955B7B0D00F37C5430FE/fulltext/tei"><teiHeader><fileDesc><titleStmt><title level="a">A background-thinning-based approach for separating and recognizing connected handwritten digit strings</title><respStmt xml:id="ISTEX-API" resp="Références bibliographiques récupérées via GROBID" name="ISTEX-API (INIST-CNRS)"></respStmt></titleStmt><publicationStmt><authority>ISTEX</authority><publisher>ELSEVIER</publisher><availability><p>ELSEVIER</p></availability><date>1999</date></publicationStmt><sourceDesc><biblStruct type="inbook"><analytic><title level="a">A background-thinning-based approach for separating and recognizing connected handwritten digit strings</title><author><persName><forename type="first">Zhongkang</forename><surname>Lu</surname></persName><affiliation>Department of Electronic Engineering, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong</affiliation></author><author><persName><forename type="first">Zheru</forename><surname>Chi</surname></persName><note type="correspondence"><p>Corresponding author</p></note><affiliation>Department of Electronic Engineering, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong</affiliation></author><author><persName><forename type="first">Wan-Chi</forename><surname>Siu</surname></persName><affiliation>Department of Electronic Engineering, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong</affiliation></author><author><persName><forename type="first">Pengfei</forename><surname>Shi</surname></persName><affiliation>Institute of Pattern Recognition & Image Processing, Shanghai Jiaotong University, Shanghai 200030, People's Republic of China</affiliation></author></analytic><monogr><title level="j">Pattern Recognition</title><title level="j" type="abbrev">PR</title><idno type="pISSN">0031-3203</idno><idno type="PII">S0031-3203(00)X0051-9</idno><imprint><publisher>ELSEVIER</publisher><date type="published" when="1997"></date><biblScope unit="volume">32</biblScope><biblScope unit="issue">6</biblScope><biblScope unit="page" from="921">921</biblScope><biblScope unit="page" to="933">933</biblScope></imprint></monogr><idno type="istex">639BFA6F63CEE00F51A5955B7B0D00F37C5430FE</idno><idno type="DOI">10.1016/S0031-3203(98)00123-X</idno><idno type="PII">S0031-3203(98)00123-X</idno></biblStruct></sourceDesc></fileDesc><profileDesc><creation><date>1999</date></creation><langUsage><language ident="en">en</language></langUsage><abstract xml:lang="en"><p>Most algorithms for segmenting connected handwritten digit strings are based on the analysis of the foreground pixel distributions and the features on the upper/lower contours of the image. In this paper, a new approach is presented to segment connected handwritten two-digit strings based on the thinning of background regions. The algorithm first locates several feature points on the background skeleton of a digit image. Possible segmentation paths are then constructed by matching these feature points. With geometric property measures, all the possible segmentation paths are ranked using fuzzy rules generated from a decision-tree approach. Finally, the top ranked segmentation paths are tested one by one by an optimized nearest neighbor classifier until one of these candidates is accepted based on an acceptance criterion. Experimental results on NIST special database 3 show that our approach can achieve a correct classification rate of 92.5% with only 4.7% of digit strings rejected, which compares favorably with the other techniques tested.</p></abstract><textClass><keywords scheme="keyword"><list><head>Keywords</head><item><term>Character recognition</term></item><item><term>Character segmentation</term></item><item><term>Connected digit strings</term></item><item><term>Thinning</term></item><item><term>Fuzzy rules</term></item></list></keywords></textClass></profileDesc><revisionDesc><change when="1997-11-17">Received</change><change when="1998-08-03">Modified</change><change when="1997">Published</change><change xml:id="refBibs-istex" who="#ISTEX-API" when="2016-3-5">References added</change></revisionDesc></teiHeader></istex:fulltextTEI><json:item><original>false</original><mimetype>text/plain</mimetype><extension>txt</extension><uri>https://api.istex.fr/document/639BFA6F63CEE00F51A5955B7B0D00F37C5430FE/fulltext/txt</uri></json:item></fulltext><metadata><istex:metadataXml wicri:clean="Elsevier converted-article found"><istex:xmlDeclaration>version="1.0" encoding="utf-8"</istex:xmlDeclaration><istex:docType PUBLIC="-//ES//DTD journal article DTD version 4.5.2//EN//XML" URI="art452.dtd" name="istex:docType"></istex:docType><istex:document><converted-article version="4.5.2" docsubtype="fla"><item-info><jid>PR</jid><aid>948</aid><ce:pii>S0031-3203(98)00123-X</ce:pii><ce:doi>10.1016/S0031-3203(98)00123-X</ce:doi><ce:copyright type="society" year="1999">Pattern Recognition Society</ce:copyright></item-info><head><ce:title>A background-thinning-based approach for separating and recognizing connected handwritten digit strings</ce:title><ce:author-group><ce:author><ce:given-name>Zhongkang</ce:given-name><ce:surname>Lu</ce:surname><ce:cross-ref refid="ORFA"><ce:sup>a</ce:sup></ce:cross-ref></ce:author><ce:author><ce:given-name>Zheru</ce:given-name><ce:surname>Chi</ce:surname><ce:cross-ref refid="ORFA"><ce:sup>a</ce:sup></ce:cross-ref><ce:cross-ref refid="COR1">*</ce:cross-ref></ce:author><ce:author><ce:given-name>Wan-Chi</ce:given-name><ce:surname>Siu</ce:surname><ce:cross-ref refid="ORFA"><ce:sup>a</ce:sup></ce:cross-ref></ce:author><ce:author><ce:given-name>Pengfei</ce:given-name><ce:surname>Shi</ce:surname><ce:cross-ref refid="ORFB"><ce:sup>b</ce:sup></ce:cross-ref></ce:author><ce:affiliation id="ORFA"><ce:label>a</ce:label><ce:textfn>Department of Electronic Engineering, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong</ce:textfn></ce:affiliation><ce:affiliation id="ORFB"><ce:label>b</ce:label><ce:textfn>Institute of Pattern Recognition & Image Processing, Shanghai Jiaotong University, Shanghai 200030, People's Republic of China</ce:textfn></ce:affiliation><ce:correspondence id="COR1"><ce:label>*</ce:label><ce:text>Corresponding author</ce:text></ce:correspondence></ce:author-group><ce:date-received day="17" month="11" year="1997"></ce:date-received><ce:date-revised day="3" month="8" year="1998"></ce:date-revised><ce:abstract><ce:section-title>Abstract</ce:section-title><ce:abstract-sec><ce:simple-para>Most algorithms for segmenting connected handwritten digit strings are based on the analysis of the foreground pixel distributions and the features on the upper/lower contours of the image. In this paper, a new approach is presented to segment connected handwritten two-digit strings based on the thinning of background regions. The algorithm first locates several feature points on the background skeleton of a digit image. Possible segmentation paths are then constructed by matching these feature points. With geometric property measures, all the possible segmentation paths are ranked using fuzzy rules generated from a decision-tree approach. Finally, the top ranked segmentation paths are tested one by one by an optimized nearest neighbor classifier until one of these candidates is accepted based on an acceptance criterion. Experimental results on NIST special database 3 show that our approach can achieve a correct classification rate of 92.5% with only 4.7% of digit strings rejected, which compares favorably with the other techniques tested.</ce:simple-para></ce:abstract-sec></ce:abstract><ce:keywords><ce:section-title>Keywords</ce:section-title><ce:keyword><ce:text>Character recognition</ce:text></ce:keyword><ce:keyword><ce:text>Character segmentation</ce:text></ce:keyword><ce:keyword><ce:text>Connected digit strings</ce:text></ce:keyword><ce:keyword><ce:text>Thinning</ce:text></ce:keyword><ce:keyword><ce:text>Fuzzy rules</ce:text></ce:keyword></ce:keywords></head></converted-article></istex:document></istex:metadataXml><mods version="3.6"><titleInfo><title>A background-thinning-based approach for separating and recognizing connected handwritten digit strings</title></titleInfo><titleInfo type="alternative" contentType="CDATA"><title>A background-thinning-based approach for separating and recognizing connected handwritten digit strings</title></titleInfo><name type="personal"><namePart type="given">Zhongkang</namePart><namePart type="family">Lu</namePart><affiliation>Department of Electronic Engineering, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong</affiliation><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">Zheru</namePart><namePart type="family">Chi</namePart><affiliation>Department of Electronic Engineering, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong</affiliation><description>Corresponding author</description><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">Wan-Chi</namePart><namePart type="family">Siu</namePart><affiliation>Department of Electronic Engineering, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong</affiliation><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">Pengfei</namePart><namePart type="family">Shi</namePart><affiliation>Institute of Pattern Recognition & Image Processing, Shanghai Jiaotong University, Shanghai 200030, People's Republic of China</affiliation><role><roleTerm type="text">author</roleTerm></role></name><typeOfResource>text</typeOfResource><genre type="research-article" displayLabel="Full-length article"></genre><originInfo><publisher>ELSEVIER</publisher><dateIssued encoding="w3cdtf">1997</dateIssued><dateCaptured encoding="w3cdtf">1997-11-17</dateCaptured><dateModified encoding="w3cdtf">1998-08-03</dateModified><copyrightDate encoding="w3cdtf">1999</copyrightDate></originInfo><language><languageTerm type="code" authority="iso639-2b">eng</languageTerm><languageTerm type="code" authority="rfc3066">en</languageTerm></language><physicalDescription><internetMediaType>text/html</internetMediaType></physicalDescription><abstract lang="en">Most algorithms for segmenting connected handwritten digit strings are based on the analysis of the foreground pixel distributions and the features on the upper/lower contours of the image. In this paper, a new approach is presented to segment connected handwritten two-digit strings based on the thinning of background regions. The algorithm first locates several feature points on the background skeleton of a digit image. Possible segmentation paths are then constructed by matching these feature points. With geometric property measures, all the possible segmentation paths are ranked using fuzzy rules generated from a decision-tree approach. Finally, the top ranked segmentation paths are tested one by one by an optimized nearest neighbor classifier until one of these candidates is accepted based on an acceptance criterion. Experimental results on NIST special database 3 show that our approach can achieve a correct classification rate of 92.5% with only 4.7% of digit strings rejected, which compares favorably with the other techniques tested.</abstract><subject><genre>Keywords</genre><topic>Character recognition</topic><topic>Character segmentation</topic><topic>Connected digit strings</topic><topic>Thinning</topic><topic>Fuzzy rules</topic></subject><relatedItem type="host"><titleInfo><title>Pattern Recognition</title></titleInfo><titleInfo type="abbreviated"><title>PR</title></titleInfo><genre type="Journal">journal</genre><originInfo><dateIssued encoding="w3cdtf">199906</dateIssued></originInfo><identifier type="ISSN">0031-3203</identifier><identifier type="PII">S0031-3203(00)X0051-9</identifier><part><date>199906</date><detail type="volume"><number>32</number><caption>vol.</caption></detail><detail type="issue"><number>6</number><caption>no.</caption></detail><extent unit="issue pages"><start>907</start><end>1082</end></extent><extent unit="pages"><start>921</start><end>933</end></extent></part></relatedItem><identifier type="istex">639BFA6F63CEE00F51A5955B7B0D00F37C5430FE</identifier><identifier type="DOI">10.1016/S0031-3203(98)00123-X</identifier><identifier type="PII">S0031-3203(98)00123-X</identifier><accessCondition type="use and reproduction" contentType="">© 1999Pattern Recognition Society</accessCondition><recordInfo><recordContentSource>ELSEVIER</recordContentSource><recordOrigin>Pattern Recognition Society, ©1999</recordOrigin></recordInfo></mods></metadata><enrichments><istex:catWosTEI uri="https://api.istex.fr/document/639BFA6F63CEE00F51A5955B7B0D00F37C5430FE/enrichments/catWos"><teiHeader><profileDesc><textClass><classCode scheme="WOS">COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE</classCode><classCode scheme="WOS">ENGINEERING, ELECTRICAL & ELECTRONIC</classCode></textClass></profileDesc></teiHeader></istex:catWosTEI><istex:refBibTEI uri="https://api.istex.fr/document/639BFA6F63CEE00F51A5955B7B0D00F37C5430FE/enrichments/refBib"><teiHeader></teiHeader><text><front></front><body></body><back><listBibl><biblStruct><analytic><title level="a" type="main">Machine printed character segmentation — an overview</title><author><persName><forename type="first">Y</forename><surname>Lu</surname></persName></author></analytic><monogr><title level="j">Pattern Recognition</title><imprint><biblScope unit="volume">28</biblScope><biblScope unit="issue">1</biblScope><biblScope unit="page" from="67" to="80"></biblScope><date type="published" when="1995"></date></imprint></monogr></biblStruct><biblStruct><analytic><title level="a" type="main">Character segmentation in hand-written words — an overview</title><author><persName><forename type="first">Y</forename><surname>Lu</surname></persName></author><author><persName><forename type="first">M</forename><surname>Shridhar</surname></persName></author></analytic><monogr><title level="j">Pattern Recognition</title><imprint><biblScope unit="volume">29</biblScope><biblScope unit="issue">1</biblScope><biblScope unit="page" from="77" to="96"></biblScope><date type="published" when="1996"></date></imprint></monogr></biblStruct><biblStruct><analytic><title level="a" type="main">Background region-based algorithm for the segmentation of connect digits</title><author><persName><forename type="first">M</forename><surname>Cheriet</surname></persName></author><author><persName><forename type="first">Y</forename><forename type="middle">S</forename><surname>Huang</surname></persName></author><author><persName><forename type="first">C</forename><forename type="middle">Y</forename><surname>Seun</surname></persName></author></analytic><monogr><title level="m">Proc. 11th Int. Conf. on Pattern Recognition</title><meeting>. 11th Int. Conf. on Pattern Recognition</meeting><imprint><date type="published" when="1992-09"></date><biblScope unit="page" from="619" to="622"></biblScope></imprint></monogr></biblStruct><biblStruct><analytic><title level="a" type="main">Segmentation of handwritten digits using contour features</title><author><persName><forename type="first">N</forename><forename type="middle">W</forename><surname>Strathy</surname></persName></author><author><persName><forename type="first">C</forename><forename type="middle">Y</forename><surname>Suen</surname></persName></author><author><persName><forename type="first">A</forename><surname>Krzyak</surname></persName></author></analytic><monogr><title level="m">Proc. ICDAR'93</title><meeting>. ICDAR'93</meeting><imprint><date type="published" when="1993"></date><biblScope unit="page" from="577" to="580"></biblScope></imprint></monogr></biblStruct><biblStruct><analytic><title level="a" type="main">Separation of single-and double-touching handwritten numeral strings</title><author><persName><forename type="first">Z</forename><surname>Chi</surname></persName></author><author><persName><forename type="first">M</forename><surname>Suters</surname></persName></author><author><persName><forename type="first">H</forename><surname>Yan</surname></persName></author></analytic><monogr><title level="j">Opt. Engng</title><imprint><biblScope unit="volume">34</biblScope><biblScope unit="issue">4</biblScope><biblScope unit="page" from="1159" to="1165"></biblScope><date type="published" when="1995"></date></imprint></monogr></biblStruct><biblStruct><analytic><title level="a" type="main">Separation of touching handwritten numerals strings based on structural analysis</title><author><persName><forename type="first">S</forename><surname>Yu</surname></persName></author><author><persName><forename type="first">H</forename><surname>Yan</surname></persName></author></analytic><monogr><title level="m">Proc. Real World Computing Symposium'97</title><meeting>. Real World Computing Symposium'97</meeting><imprint><date type="published" when="1997"></date><biblScope unit="page" from="238" to="245"></biblScope></imprint></monogr></biblStruct><biblStruct><analytic><title level="a" type="main">Vertex directed segmenta-tion of handwriten numerals</title><author><persName><forename type="first">J</forename><forename type="middle">M</forename><surname>Westall</surname></persName></author><author><persName><forename type="first">M</forename><forename type="middle">S</forename><surname>Narasimha</surname></persName></author></analytic><monogr><title level="j">Pattern Recognition</title><imprint><biblScope unit="volume">26</biblScope><biblScope unit="page" from="10" to="1993"></biblScope></imprint></monogr></biblStruct><biblStruct><analytic><author><persName><forename type="first">R</forename><forename type="middle">C</forename><surname>Gonzalez</surname></persName></author><author><persName><forename type="first">R</forename><forename type="middle">E</forename><surname>Woods</surname></persName></author></analytic><monogr><title level="m">Digital Image Processing</title></monogr></biblStruct><biblStruct><monogr><author><persName><surname>Addison-Wesley</surname></persName></author><imprint><date type="published" when="1992"></date><pubPlace>Boston</pubPlace></imprint></monogr></biblStruct><biblStruct><analytic><title level="a" type="main">Fuzzy sets</title><author><persName><forename type="first">L</forename><forename type="middle">A</forename><surname>Zadeh</surname></persName></author></analytic><monogr><title level="j">Inform. Controls</title><imprint><biblScope unit="volume">8</biblScope><biblScope unit="page" from="338" to="353"></biblScope><date type="published" when="1965"></date></imprint></monogr></biblStruct><biblStruct><analytic><title level="a" type="main">Fuzzy Algorithms: with Aplica-tions to Image Processing and Pattern Recognition</title><author><persName><forename type="first">Z</forename><surname>Chi</surname></persName></author><author><persName><forename type="first">H</forename><surname>Yang</surname></persName></author><author><persName><forename type="first">T</forename><surname>Pham</surname></persName></author></analytic><monogr><title level="j">World Scientific</title><imprint><date type="published" when="1996"></date></imprint></monogr></biblStruct><biblStruct><analytic><title level="a" type="main">Introduction of decision trees</title><author><persName><forename type="first">J</forename><forename type="middle">R</forename><surname>Quilan</surname></persName></author></analytic><monogr><title level="j">Machine Learning</title><imprint><biblScope unit="volume">1</biblScope><biblScope unit="issue">1</biblScope><biblScope unit="page" from="81" to="106"></biblScope><date type="published" when="1986"></date></imprint></monogr></biblStruct><biblStruct><analytic><title level="a" type="main">Handwritten digit recog-nition using combined id3-derived fuzzy rules and Markov chains</title><author><persName><forename type="first">Z</forename><surname>Chi</surname></persName></author><author><persName><forename type="first">M</forename><surname>Suter</surname></persName></author><author><persName><forename type="first">H</forename><surname>Yan</surname></persName></author></analytic><monogr><title level="j">Pattern Recognition</title><imprint><biblScope unit="volume">29</biblScope><biblScope unit="issue">11</biblScope><biblScope unit="page" from="1821" to="1833"></biblScope><date type="published" when="1996"></date></imprint></monogr></biblStruct><biblStruct><analytic><title level="a" type="main">Handwritten digit recognition using optimized prototypes</title><author><persName><forename type="first">H</forename><surname>Yan</surname></persName></author></analytic><monogr><title level="j">Pattern Recognition Letters</title><imprint><biblScope unit="volume">15</biblScope><biblScope unit="page" from="207" to="211"></biblScope><date type="published" when="1994"></date></imprint></monogr></biblStruct><biblStruct><monogr><title level="m" type="main">Segmentation of automatically located hand-written numeric strings, in: From Pixels to Features III: Frontiers in Handwriting Recognition</title><author><persName><forename type="first">R</forename><surname>Fenrich</surname></persName></author><imprint><date type="published" when="1992"></date><publisher>Elsevier</publisher><biblScope unit="page" from="47" to="59"></biblScope></imprint></monogr></biblStruct><biblStruct><analytic><title level="a" type="main">Segmentation methods for character recognition: from segmentation to document structure analysis</title><author><persName><forename type="first">H</forename><surname>Fujisawa</surname></persName></author><author><persName><forename type="first">N</forename><surname>Yasuaki</surname></persName></author><author><persName><forename type="first">K</forename><surname>Kurino</surname></persName></author></analytic><monogr><title level="m">Proc. IEEE</title><meeting>. IEEE</meeting><imprint><date type="published" when="1992"></date><biblScope unit="page" from="1079" to="1092"></biblScope></imprint></monogr></biblStruct><biblStruct><analytic><title level="a" type="main">Connected handwritten digit separation by optimal contour partition</title><author><persName><forename type="first">Z</forename><surname>Zhao</surname></persName></author><author><persName><forename type="first">M</forename><surname>Suters</surname></persName></author><author><persName><forename type="first">H</forename><surname>Yan</surname></persName></author></analytic><monogr><title level="m">Proc. DICTA-93 Conf. on Digital Image Computing: Techniques and Applications</title><meeting>. DICTA-93 Conf. on Digital Image Computing: Techniques and Applications</meeting><imprint><date type="published" when="1993"></date><biblScope unit="page" from="786" to="793"></biblScope></imprint></monogr></biblStruct></listBibl></back></text></istex:refBibTEI></enrichments><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 000B44 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Istex/Corpus/biblio.hfd -nk 000B44 | 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:639BFA6F63CEE00F51A5955B7B0D00F37C5430FE
|texte= A background-thinning-based approach for separating and recognizing connected handwritten digit strings
}}
| This area was generated with Dilib version V0.6.32. |  |