Recognizing on-line handwritten alphanumeric characters through flexible structural matching
Identifieur interne : 001E81 ( Main/Exploration ); précédent : 001E80; suivant : 001E82Recognizing on-line handwritten alphanumeric characters through flexible structural matching
Auteurs : Kam-Fai Chan [République populaire de Chine] ; Dit-Yan Yeung [République populaire de Chine, Hong Kong]Source :
- Pattern Recognition [ 0031-3203 ] ; 1998.
Abstract
Speed, accuracy, and flexibility are crucial to the practical use of on-line handwriting recognition. Besides, extensibility is also an important concern as we move from one domain to another which requires the character set to be extended. In this paper, we will propose a simple yet robust structural approach for recognizing on-line handwriting. Our approach is designed to achieve reasonable speed, fairly high accuracy and sufficient tolerance to variations. At the same time, it maintains a high degree of reusability and hence facilitates extensibility. Experimental results show that the recognition rates are 98.60% for digits, 98.49% for uppercase letters, 97.44% for lowercase letters, and 97.40% for the combined set. When the rejected cases are excluded from the calculation, the rates can be increased to 99.93%, 99.53%, 98.55% and 98.07%, respectively. On the average, the recognition speed is about 7.5 characters per second running in Prolog on a Sun SPARC 10 Unix workstation and the memory requirement is reasonably low. With this simple yet robust structural approach, we already have an effective and efficient on-line character recognition module. This module will be used as part of a larger system, a pen-based mathematical equation editor, which is being developed by the authors using a syntactical pattern recognition approach.
Url:
DOI: 10.1016/S0031-3203(98)00155-1
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 002175
- to stream Istex, to step Curation: 002026
- to stream Istex, to step Checkpoint: 001432
- to stream Main, to step Merge: 001F90
- to stream Main, to step Curation: 001E81
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title>Recognizing on-line handwritten alphanumeric characters through flexible structural matching</title>
<author><name sortKey="Chan, Kam Fai" sort="Chan, Kam Fai" uniqKey="Chan K" first="Kam-Fai" last="Chan">Kam-Fai Chan</name>
</author>
<author><name sortKey="Yeung, Dit Yan" sort="Yeung, Dit Yan" uniqKey="Yeung D" first="Dit-Yan" last="Yeung">Dit-Yan Yeung</name>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">ISTEX</idno>
<idno type="RBID">ISTEX:A9EE086319DD82A6EB392D2122B82C1C03CCF651</idno>
<date when="1999" year="1999">1999</date>
<idno type="doi">10.1016/S0031-3203(98)00155-1</idno>
<idno type="url">https://api.istex.fr/document/A9EE086319DD82A6EB392D2122B82C1C03CCF651/fulltext/pdf</idno>
<idno type="wicri:Area/Istex/Corpus">002175</idno>
<idno type="wicri:Area/Istex/Curation">002026</idno>
<idno type="wicri:Area/Istex/Checkpoint">001432</idno>
<idno type="wicri:doubleKey">0031-3203:1999:Chan K:recognizing:on:line</idno>
<idno type="wicri:Area/Main/Merge">001F90</idno>
<idno type="wicri:Area/Main/Curation">001E81</idno>
<idno type="wicri:Area/Main/Exploration">001E81</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title level="a">Recognizing on-line handwritten alphanumeric characters through flexible structural matching</title>
<author><name sortKey="Chan, Kam Fai" sort="Chan, Kam Fai" uniqKey="Chan K" first="Kam-Fai" last="Chan">Kam-Fai Chan</name>
<affiliation wicri:level="1"><country xml:lang="fr">République populaire de Chine</country>
<wicri:regionArea>Department of Computer Science, The Hong Kong University of Science & Technology, Clear Water Bay, Kowloon, Hong Kong</wicri:regionArea>
<wicri:noRegion>Hong Kong</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Yeung, Dit Yan" sort="Yeung, Dit Yan" uniqKey="Yeung D" first="Dit-Yan" last="Yeung">Dit-Yan Yeung</name>
<affiliation wicri:level="1"><country xml:lang="fr">République populaire de Chine</country>
<wicri:regionArea>Department of Computer Science, The Hong Kong University of Science & Technology, Clear Water Bay, Kowloon, Hong Kong</wicri:regionArea>
<wicri:noRegion>Hong Kong</wicri:noRegion>
</affiliation>
<affiliation wicri:level="1"><country wicri:rule="url">Hong Kong</country>
</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="1998">1998</date>
<biblScope unit="volume">32</biblScope>
<biblScope unit="issue">7</biblScope>
<biblScope unit="page" from="1099">1099</biblScope>
<biblScope unit="page" to="1114">1114</biblScope>
</imprint>
<idno type="ISSN">0031-3203</idno>
</series>
<idno type="istex">A9EE086319DD82A6EB392D2122B82C1C03CCF651</idno>
<idno type="DOI">10.1016/S0031-3203(98)00155-1</idno>
<idno type="PII">S0031-3203(98)00155-1</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">Speed, accuracy, and flexibility are crucial to the practical use of on-line handwriting recognition. Besides, extensibility is also an important concern as we move from one domain to another which requires the character set to be extended. In this paper, we will propose a simple yet robust structural approach for recognizing on-line handwriting. Our approach is designed to achieve reasonable speed, fairly high accuracy and sufficient tolerance to variations. At the same time, it maintains a high degree of reusability and hence facilitates extensibility. Experimental results show that the recognition rates are 98.60% for digits, 98.49% for uppercase letters, 97.44% for lowercase letters, and 97.40% for the combined set. When the rejected cases are excluded from the calculation, the rates can be increased to 99.93%, 99.53%, 98.55% and 98.07%, respectively. On the average, the recognition speed is about 7.5 characters per second running in Prolog on a Sun SPARC 10 Unix workstation and the memory requirement is reasonably low. With this simple yet robust structural approach, we already have an effective and efficient on-line character recognition module. This module will be used as part of a larger system, a pen-based mathematical equation editor, which is being developed by the authors using a syntactical pattern recognition approach.</div>
</front>
</TEI>
<affiliations><list><country><li>Hong Kong</li>
<li>République populaire de Chine</li>
</country>
</list>
<tree><country name="République populaire de Chine"><noRegion><name sortKey="Chan, Kam Fai" sort="Chan, Kam Fai" uniqKey="Chan K" first="Kam-Fai" last="Chan">Kam-Fai Chan</name>
</noRegion>
<name sortKey="Yeung, Dit Yan" sort="Yeung, Dit Yan" uniqKey="Yeung D" first="Dit-Yan" last="Yeung">Dit-Yan Yeung</name>
</country>
<country name="Hong Kong"><noRegion><name sortKey="Yeung, Dit Yan" sort="Yeung, Dit Yan" uniqKey="Yeung D" first="Dit-Yan" last="Yeung">Dit-Yan Yeung</name>
</noRegion>
</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 001E81 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 001E81 | 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= ISTEX:A9EE086319DD82A6EB392D2122B82C1C03CCF651 |texte= Recognizing on-line handwritten alphanumeric characters through flexible structural matching }}
This area was generated with Dilib version V0.6.32. |