Fuzzy approach to solve the recognition problem of handwritten chinese characters
Identifieur interne : 001665 ( Istex/Corpus ); précédent : 001664; suivant : 001666Fuzzy approach to solve the recognition problem of handwritten chinese characters
Auteurs : Fang-Hsuan Cheng ; Wen-Hsing Hsu ; Chien-An ChenSource :
- Pattern Recognition [ 0031-3203 ] ; 1988.
Abstract
A method based on the concept of fuzzy set for handwritten Chinese character (HCC) recognition is proposed in this paper. Chinese characters can be viewed as a collection of line segments, called strokes. Since the strokes under consideration here are fuzzy in nature, the concept of fuzzy set is utilized in the similarity measure. Two membership functions are defined for the location measure and type measure between two strokes, and a function of fuzzy entropy is used in information measure. Although the recognition problem can be reduced to the assignment problem, some modifications are still necessary. All the similarities between the corresponding strokes can be chosen by solving the assignment problem using the cost function of fuzzy entropy, and then are averaged to derive the score of similarity between two Chinese characters. 881 classes of Chinese characters in ETL-8 (160 variations/class) are used as the test patterns, and the recognition rate is about 96%.In addition, experiments about the effects of the membership function based on the class separability are also discussed in this paper.
Url:
DOI: 10.1016/0031-3203(89)90060-5
Links to Exploration step
ISTEX:4B30412950383EA5CE3A419E87B02ECC98AE6AEFLe document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title>Fuzzy approach to solve the recognition problem of handwritten chinese characters</title><author><name sortKey="Cheng, Fang Hsuan" sort="Cheng, Fang Hsuan" uniqKey="Cheng F" first="Fang-Hsuan" last="Cheng">Fang-Hsuan Cheng</name><affiliation><mods:affiliation>Institute of Electrical Engineering, National Tsing Hua University, 101 Sec. 2, Kuang Fu Rd, Hsinchu, Taiwan 30043, R.O.C.</mods:affiliation></affiliation></author><author><name sortKey="Hsu, Wen Hsing" sort="Hsu, Wen Hsing" uniqKey="Hsu W" first="Wen-Hsing" last="Hsu">Wen-Hsing Hsu</name><affiliation><mods:affiliation>Institute of Electrical Engineering, National Tsing Hua University, 101 Sec. 2, Kuang Fu Rd, Hsinchu, Taiwan 30043, R.O.C.</mods:affiliation></affiliation></author><author><name sortKey="Chen, Chien An" sort="Chen, Chien An" uniqKey="Chen C" first="Chien-An" last="Chen">Chien-An Chen</name><affiliation><mods:affiliation>Institute of Electrical Engineering, National Tsing Hua University, 101 Sec. 2, Kuang Fu Rd, Hsinchu, Taiwan 30043, R.O.C.</mods:affiliation></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:4B30412950383EA5CE3A419E87B02ECC98AE6AEF</idno><date when="1989" year="1989">1989</date><idno type="doi">10.1016/0031-3203(89)90060-5</idno><idno type="url">https://api.istex.fr/document/4B30412950383EA5CE3A419E87B02ECC98AE6AEF/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">001665</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a">Fuzzy approach to solve the recognition problem of handwritten chinese characters</title><author><name sortKey="Cheng, Fang Hsuan" sort="Cheng, Fang Hsuan" uniqKey="Cheng F" first="Fang-Hsuan" last="Cheng">Fang-Hsuan Cheng</name><affiliation><mods:affiliation>Institute of Electrical Engineering, National Tsing Hua University, 101 Sec. 2, Kuang Fu Rd, Hsinchu, Taiwan 30043, R.O.C.</mods:affiliation></affiliation></author><author><name sortKey="Hsu, Wen Hsing" sort="Hsu, Wen Hsing" uniqKey="Hsu W" first="Wen-Hsing" last="Hsu">Wen-Hsing Hsu</name><affiliation><mods:affiliation>Institute of Electrical Engineering, National Tsing Hua University, 101 Sec. 2, Kuang Fu Rd, Hsinchu, Taiwan 30043, R.O.C.</mods:affiliation></affiliation></author><author><name sortKey="Chen, Chien An" sort="Chen, Chien An" uniqKey="Chen C" first="Chien-An" last="Chen">Chien-An Chen</name><affiliation><mods:affiliation>Institute of Electrical Engineering, National Tsing Hua University, 101 Sec. 2, Kuang Fu Rd, Hsinchu, Taiwan 30043, R.O.C.</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="1988">1988</date><biblScope unit="volume">22</biblScope><biblScope unit="issue">2</biblScope><biblScope unit="page" from="133">133</biblScope><biblScope unit="page" to="141">141</biblScope></imprint><idno type="ISSN">0031-3203</idno></series><idno type="istex">4B30412950383EA5CE3A419E87B02ECC98AE6AEF</idno><idno type="DOI">10.1016/0031-3203(89)90060-5</idno><idno type="PII">0031-3203(89)90060-5</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">A method based on the concept of fuzzy set for handwritten Chinese character (HCC) recognition is proposed in this paper. Chinese characters can be viewed as a collection of line segments, called strokes. Since the strokes under consideration here are fuzzy in nature, the concept of fuzzy set is utilized in the similarity measure. Two membership functions are defined for the location measure and type measure between two strokes, and a function of fuzzy entropy is used in information measure. Although the recognition problem can be reduced to the assignment problem, some modifications are still necessary. All the similarities between the corresponding strokes can be chosen by solving the assignment problem using the cost function of fuzzy entropy, and then are averaged to derive the score of similarity between two Chinese characters. 881 classes of Chinese characters in ETL-8 (160 variations/class) are used as the test patterns, and the recognition rate is about 96%.In addition, experiments about the effects of the membership function based on the class separability are also discussed in this paper.</div></front></TEI><istex><corpusName>elsevier</corpusName><author><json:item><name>Fang-Hsuan Cheng</name><affiliations><json:string>Institute of Electrical Engineering, National Tsing Hua University, 101 Sec. 2, Kuang Fu Rd, Hsinchu, Taiwan 30043, R.O.C.</json:string></affiliations></json:item><json:item><name>Wen-Hsing Hsu</name><affiliations><json:string>Institute of Electrical Engineering, National Tsing Hua University, 101 Sec. 2, Kuang Fu Rd, Hsinchu, Taiwan 30043, R.O.C.</json:string></affiliations></json:item><json:item><name>Chien-An Chen</name><affiliations><json:string>Institute of Electrical Engineering, National Tsing Hua University, 101 Sec. 2, Kuang Fu Rd, Hsinchu, Taiwan 30043, R.O.C.</json:string></affiliations></json:item></author><subject><json:item><lang><json:string>eng</json:string></lang><value>Similarity measure</value></json:item><json:item><lang><json:string>eng</json:string></lang><value>Membership function</value></json:item><json:item><lang><json:string>eng</json:string></lang><value>Assignment problem</value></json:item><json:item><lang><json:string>eng</json:string></lang><value>Fuzzy entropy</value></json:item><json:item><lang><json:string>eng</json:string></lang><value>Probabilistic metric space</value></json:item><json:item><lang><json:string>eng</json:string></lang><value>Class separability</value></json:item></subject><language><json:string>eng</json:string></language><abstract>A method based on the concept of fuzzy set for handwritten Chinese character (HCC) recognition is proposed in this paper. Chinese characters can be viewed as a collection of line segments, called strokes. Since the strokes under consideration here are fuzzy in nature, the concept of fuzzy set is utilized in the similarity measure. Two membership functions are defined for the location measure and type measure between two strokes, and a function of fuzzy entropy is used in information measure. Although the recognition problem can be reduced to the assignment problem, some modifications are still necessary. All the similarities between the corresponding strokes can be chosen by solving the assignment problem using the cost function of fuzzy entropy, and then are averaged to derive the score of similarity between two Chinese characters. 881 classes of Chinese characters in ETL-8 (160 variations/class) are used as the test patterns, and the recognition rate is about 96%.In addition, experiments about the effects of the membership function based on the class separability are also discussed in this paper.</abstract><qualityIndicators><score>6.563</score><pdfVersion>1.2</pdfVersion><pdfPageSize>526 x 778 pts</pdfPageSize><refBibsNative>true</refBibsNative><keywordCount>6</keywordCount><abstractCharCount>1115</abstractCharCount><pdfWordCount>4475</pdfWordCount><pdfCharCount>27163</pdfCharCount><pdfPageCount>9</pdfPageCount><abstractWordCount>174</abstractWordCount></qualityIndicators><title>Fuzzy approach to solve the recognition problem of handwritten chinese characters</title><pii><json:string>0031-3203(89)90060-5</json:string></pii><genre><json:string>research-article</json:string></genre><host><volume>22</volume><pii><json:string>S0031-3203(00)X0208-7</json:string></pii><pages><last>141</last><first>133</first></pages><issn><json:string>0031-3203</json:string></issn><issue>2</issue><genre><json:string>Journal</json:string></genre><language><json:string>unknown</json:string></language><title>Pattern Recognition</title><publicationDate>1989</publicationDate></host><categories><wos><json:string>COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE</json:string><json:string>ENGINEERING, ELECTRICAL & ELECTRONIC</json:string></wos></categories><publicationDate>1988</publicationDate><copyrightDate>1989</copyrightDate><doi><json:string>10.1016/0031-3203(89)90060-5</json:string></doi><id>4B30412950383EA5CE3A419E87B02ECC98AE6AEF</id><fulltext><json:item><original>true</original><mimetype>application/pdf</mimetype><extension>pdf</extension><uri>https://api.istex.fr/document/4B30412950383EA5CE3A419E87B02ECC98AE6AEF/fulltext/pdf</uri></json:item><json:item><original>true</original><mimetype>text/plain</mimetype><extension>txt</extension><uri>https://api.istex.fr/document/4B30412950383EA5CE3A419E87B02ECC98AE6AEF/fulltext/txt</uri></json:item><json:item><original>false</original><mimetype>application/zip</mimetype><extension>zip</extension><uri>https://api.istex.fr/document/4B30412950383EA5CE3A419E87B02ECC98AE6AEF/fulltext/zip</uri></json:item><istex:fulltextTEI uri="https://api.istex.fr/document/4B30412950383EA5CE3A419E87B02ECC98AE6AEF/fulltext/tei"><teiHeader><fileDesc><titleStmt><title level="a">Fuzzy approach to solve the recognition problem of handwritten chinese characters</title></titleStmt><publicationStmt><authority>ISTEX</authority><publisher>ELSEVIER</publisher><availability><p>ELSEVIER</p></availability><date>1989</date></publicationStmt><sourceDesc><biblStruct type="inbook"><analytic><title level="a">Fuzzy approach to solve the recognition problem of handwritten chinese characters</title><author><persName><forename type="first">Fang-Hsuan</forename><surname>Cheng</surname></persName><affiliation>Institute of Electrical Engineering, National Tsing Hua University, 101 Sec. 2, Kuang Fu Rd, Hsinchu, Taiwan 30043, R.O.C.</affiliation></author><author><persName><forename type="first">Wen-Hsing</forename><surname>Hsu</surname></persName><note type="biography">The author is also with the Institute of Information Science, Academia Sinica, Taipei, Taiwan.</note><affiliation>The author is also with the Institute of Information Science, Academia Sinica, Taipei, Taiwan.</affiliation><affiliation>Institute of Electrical Engineering, National Tsing Hua University, 101 Sec. 2, Kuang Fu Rd, Hsinchu, Taiwan 30043, R.O.C.</affiliation></author><author><persName><forename type="first">Chien-An</forename><surname>Chen</surname></persName><affiliation>Institute of Electrical Engineering, National Tsing Hua University, 101 Sec. 2, Kuang Fu Rd, Hsinchu, Taiwan 30043, R.O.C.</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)X0208-7</idno><imprint><publisher>ELSEVIER</publisher><date type="published" when="1988"></date><biblScope unit="volume">22</biblScope><biblScope unit="issue">2</biblScope><biblScope unit="page" from="133">133</biblScope><biblScope unit="page" to="141">141</biblScope></imprint></monogr><idno type="istex">4B30412950383EA5CE3A419E87B02ECC98AE6AEF</idno><idno type="DOI">10.1016/0031-3203(89)90060-5</idno><idno type="PII">0031-3203(89)90060-5</idno></biblStruct></sourceDesc></fileDesc><profileDesc><creation><date>1989</date></creation><langUsage><language ident="en">en</language></langUsage><abstract xml:lang="en"><p>A method based on the concept of fuzzy set for handwritten Chinese character (HCC) recognition is proposed in this paper. Chinese characters can be viewed as a collection of line segments, called strokes. Since the strokes under consideration here are fuzzy in nature, the concept of fuzzy set is utilized in the similarity measure. Two membership functions are defined for the location measure and type measure between two strokes, and a function of fuzzy entropy is used in information measure. Although the recognition problem can be reduced to the assignment problem, some modifications are still necessary. All the similarities between the corresponding strokes can be chosen by solving the assignment problem using the cost function of fuzzy entropy, and then are averaged to derive the score of similarity between two Chinese characters. 881 classes of Chinese characters in ETL-8 (160 variations/class) are used as the test patterns, and the recognition rate is about 96%.In addition, experiments about the effects of the membership function based on the class separability are also discussed in this paper.</p></abstract><textClass><keywords scheme="keyword"><list><head>Keywords</head><item><term>Similarity measure</term></item><item><term>Membership function</term></item><item><term>Assignment problem</term></item><item><term>Fuzzy entropy</term></item><item><term>Probabilistic metric space</term></item><item><term>Class separability</term></item></list></keywords></textClass></profileDesc><revisionDesc><change when="1988-06-07">Registration</change><change when="1988-05-20">Modified</change><change when="1988">Published</change></revisionDesc></teiHeader></istex:fulltextTEI></fulltext><metadata><istex:metadataXml wicri:clean="Elsevier, elements deleted: tail"><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>89900605</aid><ce:pii>0031-3203(89)90060-5</ce:pii><ce:doi>10.1016/0031-3203(89)90060-5</ce:doi><ce:copyright type="unknown" year="1989"></ce:copyright></item-info><head><ce:title>Fuzzy approach to solve the recognition problem of handwritten chinese characters</ce:title><ce:author-group><ce:author><ce:given-name>Fang-Hsuan</ce:given-name><ce:surname>Cheng</ce:surname></ce:author><ce:author><ce:given-name>Wen-Hsing</ce:given-name><ce:surname>Hsu</ce:surname><ce:cross-ref refid="FN1"><ce:sup>∗</ce:sup></ce:cross-ref></ce:author><ce:author><ce:given-name>Chien-An</ce:given-name><ce:surname>Chen</ce:surname></ce:author><ce:affiliation><ce:textfn>Institute of Electrical Engineering, National Tsing Hua University, 101 Sec. 2, Kuang Fu Rd, Hsinchu, Taiwan 30043, R.O.C.</ce:textfn></ce:affiliation><ce:footnote id="FN1"><ce:label>∗</ce:label><ce:note-para>The author is also with the Institute of Information Science, Academia Sinica, Taipei, Taiwan.</ce:note-para></ce:footnote></ce:author-group><ce:date-received day="11" month="12" year="1987"></ce:date-received><ce:date-revised day="20" month="5" year="1988"></ce:date-revised><ce:date-accepted day="7" month="6" year="1988"></ce:date-accepted><ce:abstract><ce:section-title>Abstract</ce:section-title><ce:abstract-sec><ce:simple-para>A method based on the concept of fuzzy set for handwritten Chinese character (HCC) recognition is proposed in this paper. Chinese characters can be viewed as a collection of line segments, called strokes. Since the strokes under consideration here are fuzzy in nature, the concept of fuzzy set is utilized in the similarity measure. Two membership functions are defined for the location measure and type measure between two strokes, and a function of fuzzy entropy is used in information measure. Although the recognition problem can be reduced to the assignment problem, some modifications are still necessary. All the similarities between the corresponding strokes can be chosen by solving the assignment problem using the cost function of fuzzy entropy, and then are averaged to derive the score of similarity between two Chinese characters. 881 classes of Chinese characters in ETL-8 (160 variations/class) are used as the test patterns, and the recognition rate is about 96%.</ce:simple-para><ce:simple-para>In addition, experiments about the effects of the membership function based on the class separability are also discussed in this paper.</ce:simple-para></ce:abstract-sec></ce:abstract><ce:keywords><ce:section-title>Keywords</ce:section-title><ce:keyword><ce:text>Similarity measure</ce:text></ce:keyword><ce:keyword><ce:text>Membership function</ce:text></ce:keyword><ce:keyword><ce:text>Assignment problem</ce:text></ce:keyword><ce:keyword><ce:text>Fuzzy entropy</ce:text></ce:keyword><ce:keyword><ce:text>Probabilistic metric space</ce:text></ce:keyword><ce:keyword><ce:text>Class separability</ce:text></ce:keyword></ce:keywords></head></converted-article></istex:document></istex:metadataXml><mods version="3.6"><titleInfo><title>Fuzzy approach to solve the recognition problem of handwritten chinese characters</title></titleInfo><titleInfo type="alternative" contentType="CDATA"><title>Fuzzy approach to solve the recognition problem of handwritten chinese characters</title></titleInfo><name type="personal"><namePart type="given">Fang-Hsuan</namePart><namePart type="family">Cheng</namePart><affiliation>Institute of Electrical Engineering, National Tsing Hua University, 101 Sec. 2, Kuang Fu Rd, Hsinchu, Taiwan 30043, R.O.C.</affiliation><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">Wen-Hsing</namePart><namePart type="family">Hsu</namePart><affiliation>Institute of Electrical Engineering, National Tsing Hua University, 101 Sec. 2, Kuang Fu Rd, Hsinchu, Taiwan 30043, R.O.C.</affiliation><description>The author is also with the Institute of Information Science, Academia Sinica, Taipei, Taiwan.</description><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">Chien-An</namePart><namePart type="family">Chen</namePart><affiliation>Institute of Electrical Engineering, National Tsing Hua University, 101 Sec. 2, Kuang Fu Rd, Hsinchu, Taiwan 30043, R.O.C.</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">1988</dateIssued><dateValid encoding="w3cdtf">1988-06-07</dateValid><dateModified encoding="w3cdtf">1988-05-20</dateModified><copyrightDate encoding="w3cdtf">1989</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">A method based on the concept of fuzzy set for handwritten Chinese character (HCC) recognition is proposed in this paper. Chinese characters can be viewed as a collection of line segments, called strokes. Since the strokes under consideration here are fuzzy in nature, the concept of fuzzy set is utilized in the similarity measure. Two membership functions are defined for the location measure and type measure between two strokes, and a function of fuzzy entropy is used in information measure. Although the recognition problem can be reduced to the assignment problem, some modifications are still necessary. All the similarities between the corresponding strokes can be chosen by solving the assignment problem using the cost function of fuzzy entropy, and then are averaged to derive the score of similarity between two Chinese characters. 881 classes of Chinese characters in ETL-8 (160 variations/class) are used as the test patterns, and the recognition rate is about 96%.In addition, experiments about the effects of the membership function based on the class separability are also discussed in this paper.</abstract><subject><genre>Keywords</genre><topic>Similarity measure</topic><topic>Membership function</topic><topic>Assignment problem</topic><topic>Fuzzy entropy</topic><topic>Probabilistic metric space</topic><topic>Class separability</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">1989</dateIssued></originInfo><identifier type="ISSN">0031-3203</identifier><identifier type="PII">S0031-3203(00)X0208-7</identifier><part><date>1989</date><detail type="volume"><number>22</number><caption>vol.</caption></detail><detail type="issue"><number>2</number><caption>no.</caption></detail><extent unit="issue pages"><start>97</start><end>223</end></extent><extent unit="pages"><start>133</start><end>141</end></extent></part></relatedItem><identifier type="istex">4B30412950383EA5CE3A419E87B02ECC98AE6AEF</identifier><identifier type="DOI">10.1016/0031-3203(89)90060-5</identifier><identifier type="PII">0031-3203(89)90060-5</identifier><recordInfo><recordContentSource>ELSEVIER</recordContentSource></recordInfo></mods></metadata><enrichments><istex:catWosTEI uri="https://api.istex.fr/document/4B30412950383EA5CE3A419E87B02ECC98AE6AEF/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></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 001665 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Istex/Corpus/biblio.hfd -nk 001665 | 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:4B30412950383EA5CE3A419E87B02ECC98AE6AEF
|texte= Fuzzy approach to solve the recognition problem of handwritten chinese characters
}}
| This area was generated with Dilib version V0.6.32. |  |