Automatic feature design for optical character recognition using an evolutionary search procedure.
Identifieur interne : 000112 ( Ncbi/Curation ); précédent : 000111; suivant : 000113Automatic feature design for optical character recognition using an evolutionary search procedure.
Auteurs : F W Stentiford [Royaume-Uni]Source :
- IEEE transactions on pattern analysis and machine intelligence [ 0162-8828 ] ; 1985.
Abstract
An automatic evolutionary search is applied to the problem of feature extraction in an OCR application. A performance measure based on feature independence is used to generate features which do not appear to suffer from peaking effects [17]. Features are extracted from a training set of 30 600 machine printed 34 class alphanumeric characters derived from British mail. Classification results on the training set and a test set of 10 200 characters are reported for an increasing number of features. A 1.01 percent forced decision error rate is obtained on the test data using 316 features. The hardware implementation should be cheap and fast to operate. The performance compares favorably with current low cost OCR page readers.
PubMed: 21869271
Links toward previous steps (curation, corpus...)
- to stream PubMed, to step Corpus: Pour aller vers cette notice dans l'étape Curation :000091
- to stream PubMed, to step Curation: Pour aller vers cette notice dans l'étape Curation :000091
- to stream PubMed, to step Checkpoint: Pour aller vers cette notice dans l'étape Curation :000091
- to stream Ncbi, to step Merge: Pour aller vers cette notice dans l'étape Curation :000112
Links to Exploration step
pubmed:21869271Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">Automatic feature design for optical character recognition using an evolutionary search procedure.</title>
<author><name sortKey="Stentiford, F W" sort="Stentiford, F W" uniqKey="Stentiford F" first="F W" last="Stentiford">F W Stentiford</name>
<affiliation wicri:level="2"><nlm:affiliation>British Telecom Research Laboratories. Ipswich, Suffolk, England.</nlm:affiliation>
<country>Royaume-Uni</country>
<placeName><region type="country">Angleterre</region>
</placeName>
<wicri:cityArea>British Telecom Research Laboratories. Ipswich, Suffolk</wicri:cityArea>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">PubMed</idno>
<date when="1985">1985</date>
<idno type="RBID">pubmed:21869271</idno>
<idno type="pmid">21869271</idno>
<idno type="wicri:Area/PubMed/Corpus">000091</idno>
<idno type="wicri:Area/PubMed/Curation">000091</idno>
<idno type="wicri:Area/PubMed/Checkpoint">000091</idno>
<idno type="wicri:Area/Ncbi/Merge">000112</idno>
<idno type="wicri:Area/Ncbi/Curation">000112</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en">Automatic feature design for optical character recognition using an evolutionary search procedure.</title>
<author><name sortKey="Stentiford, F W" sort="Stentiford, F W" uniqKey="Stentiford F" first="F W" last="Stentiford">F W Stentiford</name>
<affiliation wicri:level="2"><nlm:affiliation>British Telecom Research Laboratories. Ipswich, Suffolk, England.</nlm:affiliation>
<country>Royaume-Uni</country>
<placeName><region type="country">Angleterre</region>
</placeName>
<wicri:cityArea>British Telecom Research Laboratories. Ipswich, Suffolk</wicri:cityArea>
</affiliation>
</author>
</analytic>
<series><title level="j">IEEE transactions on pattern analysis and machine intelligence</title>
<idno type="ISSN">0162-8828</idno>
<imprint><date when="1985" type="published">1985</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><textClass></textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">An automatic evolutionary search is applied to the problem of feature extraction in an OCR application. A performance measure based on feature independence is used to generate features which do not appear to suffer from peaking effects [17]. Features are extracted from a training set of 30 600 machine printed 34 class alphanumeric characters derived from British mail. Classification results on the training set and a test set of 10 200 characters are reported for an increasing number of features. A 1.01 percent forced decision error rate is obtained on the test data using 316 features. The hardware implementation should be cheap and fast to operate. The performance compares favorably with current low cost OCR page readers.</div>
</front>
</TEI>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/Ncbi/Curation
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000112 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Ncbi/Curation/biblio.hfd -nk 000112 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Ticri/CIDE |area= OcrV1 |flux= Ncbi |étape= Curation |type= RBID |clé= pubmed:21869271 |texte= Automatic feature design for optical character recognition using an evolutionary search procedure. }}
Pour générer des pages wiki
HfdIndexSelect -h $EXPLOR_AREA/Data/Ncbi/Curation/RBID.i -Sk "pubmed:21869271" \ | HfdSelect -Kh $EXPLOR_AREA/Data/Ncbi/Curation/biblio.hfd \ | NlmPubMed2Wicri -a OcrV1
![]() | This area was generated with Dilib version V0.6.32. | ![]() |