Template-based online character recognition
Identifieur interne : 001C45 ( Main/Exploration ); précédent : 001C44; suivant : 001C46Template-based online character recognition
Auteurs : Scott D. Connell [États-Unis] ; Anil K. Jain [États-Unis]Source :
- Pattern Recognition [ 0031-3203 ] ; 1999.
Abstract
Handwriting is a common, natural form of communication for humans, and therefore it is useful to utilize this modality as a means of input to machines. One well-known method of classifying individual characters or words is template matching. We demonstrate a template-based system for online character recognition where the number of representative templates is determined automatically. These templates can be viewed as representing different styles of writing a particular character. The templates are then used as a reference for efficient classification using decision trees. Overall, our classifier achieves an 86.9% accuracy on a set of 17,928 alphanumeric characters (36 classes; 10 digits and 26 lowercase letters) with a throughput of over 8 characters per second on a 296 MHz Sun UltraSparc.
Url:
DOI: 10.1016/S0031-3203(99)00197-1
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 002820
- to stream Istex, to step Curation: 002629
- to stream Istex, to step Checkpoint: 001247
- to stream Main, to step Merge: 001D44
- to stream Main, to step Curation: 001C45
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title>Template-based online character recognition</title>
<author><name sortKey="Connell, Scott D" sort="Connell, Scott D" uniqKey="Connell S" first="Scott D." last="Connell">Scott D. Connell</name>
</author>
<author><name sortKey="Jain, Anil K" sort="Jain, Anil K" uniqKey="Jain A" first="Anil K." last="Jain">Anil K. Jain</name>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">ISTEX</idno>
<idno type="RBID">ISTEX:C585285932C67CC4EC163BBF974FCA82BAE67BD6</idno>
<date when="2000" year="2000">2000</date>
<idno type="doi">10.1016/S0031-3203(99)00197-1</idno>
<idno type="url">https://api.istex.fr/document/C585285932C67CC4EC163BBF974FCA82BAE67BD6/fulltext/pdf</idno>
<idno type="wicri:Area/Istex/Corpus">002820</idno>
<idno type="wicri:Area/Istex/Curation">002629</idno>
<idno type="wicri:Area/Istex/Checkpoint">001247</idno>
<idno type="wicri:doubleKey">0031-3203:2000:Connell S:template:based:online</idno>
<idno type="wicri:Area/Main/Merge">001D44</idno>
<idno type="wicri:Area/Main/Curation">001C45</idno>
<idno type="wicri:Area/Main/Exploration">001C45</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title level="a">Template-based online character recognition</title>
<author><name sortKey="Connell, Scott D" sort="Connell, Scott D" uniqKey="Connell S" first="Scott D." last="Connell">Scott D. Connell</name>
<affiliation wicri:level="4"><country xml:lang="fr">États-Unis</country>
<wicri:regionArea>Department of Computer Science and Engineering, Michigan State University, East Lansing, MI 48824</wicri:regionArea>
<placeName><region type="state">Michigan</region>
<settlement type="city">East Lansing</settlement>
</placeName>
<orgName type="university">Université d'État du Michigan</orgName>
</affiliation>
<affiliation wicri:level="1"><country wicri:rule="url">États-Unis</country>
</affiliation>
</author>
<author><name sortKey="Jain, Anil K" sort="Jain, Anil K" uniqKey="Jain A" first="Anil K." last="Jain">Anil K. Jain</name>
<affiliation wicri:level="4"><country xml:lang="fr">États-Unis</country>
<wicri:regionArea>Department of Computer Science and Engineering, Michigan State University, East Lansing, MI 48824</wicri:regionArea>
<placeName><region type="state">Michigan</region>
<settlement type="city">East Lansing</settlement>
</placeName>
<orgName type="university">Université d'État du Michigan</orgName>
</affiliation>
<affiliation wicri:level="1"><country wicri:rule="url">États-Unis</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="1999">1999</date>
<biblScope unit="volume">34</biblScope>
<biblScope unit="issue">1</biblScope>
<biblScope unit="page" from="1">1</biblScope>
<biblScope unit="page" to="14">14</biblScope>
</imprint>
<idno type="ISSN">0031-3203</idno>
</series>
<idno type="istex">C585285932C67CC4EC163BBF974FCA82BAE67BD6</idno>
<idno type="DOI">10.1016/S0031-3203(99)00197-1</idno>
<idno type="PII">S0031-3203(99)00197-1</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">Handwriting is a common, natural form of communication for humans, and therefore it is useful to utilize this modality as a means of input to machines. One well-known method of classifying individual characters or words is template matching. We demonstrate a template-based system for online character recognition where the number of representative templates is determined automatically. These templates can be viewed as representing different styles of writing a particular character. The templates are then used as a reference for efficient classification using decision trees. Overall, our classifier achieves an 86.9% accuracy on a set of 17,928 alphanumeric characters (36 classes; 10 digits and 26 lowercase letters) with a throughput of over 8 characters per second on a 296 MHz Sun UltraSparc.</div>
</front>
</TEI>
<affiliations><list><country><li>États-Unis</li>
</country>
<region><li>Michigan</li>
</region>
<settlement><li>East Lansing</li>
</settlement>
<orgName><li>Université d'État du Michigan</li>
</orgName>
</list>
<tree><country name="États-Unis"><region name="Michigan"><name sortKey="Connell, Scott D" sort="Connell, Scott D" uniqKey="Connell S" first="Scott D." last="Connell">Scott D. Connell</name>
</region>
<name sortKey="Connell, Scott D" sort="Connell, Scott D" uniqKey="Connell S" first="Scott D." last="Connell">Scott D. Connell</name>
<name sortKey="Jain, Anil K" sort="Jain, Anil K" uniqKey="Jain A" first="Anil K." last="Jain">Anil K. Jain</name>
<name sortKey="Jain, Anil K" sort="Jain, Anil K" uniqKey="Jain A" first="Anil K." last="Jain">Anil K. Jain</name>
</country>
</tree>
</affiliations>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 001C45 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 001C45 | 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:C585285932C67CC4EC163BBF974FCA82BAE67BD6 |texte= Template-based online character recognition }}
This area was generated with Dilib version V0.6.32. |