Simulated annealing clustering of Chinese words for contextual text recognition
Identifieur interne : 002A17 ( Main/Merge ); précédent : 002A16; suivant : 002A18Simulated annealing clustering of Chinese words for contextual text recognition
Auteurs : C.-H. Chang [Taïwan]Source :
- Pattern recognition letters [ 0167-8655 ] ; 1996.
Descripteurs français
- Pascal (Inist)
- Wicri :
- topic : Stockage.
English descriptors
- KwdEn :
Abstract
Simulated annealing clustering algorithms are applied in discovering word classes in a Chinese class n-gram model, which can be used for contextual postprocessing of handwritten Chinese character recognition. Experimental results show that the proposed model achieves much better performance than the dictionary-based models and outperforms the well-known inter-word character bigram model while using less storage.
Links toward previous steps (curation, corpus...)
- to stream PascalFrancis, to step Corpus: 000A21
- to stream PascalFrancis, to step Curation: 000977
- to stream PascalFrancis, to step Checkpoint: 000930
Links to Exploration step
Pascal:96-0106676Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Simulated annealing clustering of Chinese words for contextual text recognition</title>
<author><name sortKey="Chang, C H" sort="Chang, C H" uniqKey="Chang C" first="C.-H." last="Chang">C.-H. Chang</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Industrial technology res. inst., E000/CCL</s1>
<s2>Hsinchu 31015</s2>
<s3>TWN</s3>
</inist:fA14>
<country>Taïwan</country>
<wicri:noRegion>Hsinchu 31015</wicri:noRegion>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">96-0106676</idno>
<date when="1996">1996</date>
<idno type="stanalyst">PASCAL 96-0106676 INIST</idno>
<idno type="RBID">Pascal:96-0106676</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000A21</idno>
<idno type="wicri:Area/PascalFrancis/Curation">000977</idno>
<idno type="wicri:Area/PascalFrancis/Checkpoint">000930</idno>
<idno type="wicri:doubleKey">0167-8655:1996:Chang C:simulated:annealing:clustering</idno>
<idno type="wicri:Area/Main/Merge">002A17</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Simulated annealing clustering of Chinese words for contextual text recognition</title>
<author><name sortKey="Chang, C H" sort="Chang, C H" uniqKey="Chang C" first="C.-H." last="Chang">C.-H. Chang</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Industrial technology res. inst., E000/CCL</s1>
<s2>Hsinchu 31015</s2>
<s3>TWN</s3>
</inist:fA14>
<country>Taïwan</country>
<wicri:noRegion>Hsinchu 31015</wicri:noRegion>
</affiliation>
</author>
</analytic>
<series><title level="j" type="main">Pattern recognition letters</title>
<title level="j" type="abbreviated">Pattern recogn. lett.</title>
<idno type="ISSN">0167-8655</idno>
<imprint><date when="1996">1996</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><title level="j" type="main">Pattern recognition letters</title>
<title level="j" type="abbreviated">Pattern recogn. lett.</title>
<idno type="ISSN">0167-8655</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Aggregation</term>
<term>Algorithm</term>
<term>Character recognition</term>
<term>OCR</term>
<term>Simulated annealing</term>
<term>Storage</term>
<term>Word</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Algorithme</term>
<term>Recuit simulé</term>
<term>Reconnaissance caractère</term>
<term>Agrégation</term>
<term>Mot</term>
<term>Stockage</term>
<term>Word clustering</term>
<term>Perplexity</term>
<term>Contextual postprocessing</term>
<term>OCR</term>
</keywords>
<keywords scheme="Wicri" type="topic" xml:lang="fr"><term>Stockage</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">Simulated annealing clustering algorithms are applied in discovering word classes in a Chinese class n-gram model, which can be used for contextual postprocessing of handwritten Chinese character recognition. Experimental results show that the proposed model achieves much better performance than the dictionary-based models and outperforms the well-known inter-word character bigram model while using less storage.</div>
</front>
</TEI>
<affiliations><list><country><li>Taïwan</li>
</country>
</list>
<tree><country name="Taïwan"><noRegion><name sortKey="Chang, C H" sort="Chang, C H" uniqKey="Chang C" first="C.-H." last="Chang">C.-H. Chang</name>
</noRegion>
</country>
</tree>
</affiliations>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/Main/Merge
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 002A17 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Merge/biblio.hfd -nk 002A17 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Ticri/CIDE |area= OcrV1 |flux= Main |étape= Merge |type= RBID |clé= Pascal:96-0106676 |texte= Simulated annealing clustering of Chinese words for contextual text recognition }}
This area was generated with Dilib version V0.6.32. |