Text identification for document image analysis using a neural network
Identifieur interne : 002089 ( Main/Exploration ); précédent : 002088; suivant : 002090Text identification for document image analysis using a neural network
Auteurs : C. Strouthopoulos [Grèce] ; N. Papamarkos [Grèce]Source :
- Image and Vision Computing [ 0262-8856 ] ; 1997.
Abstract
A new bottom-up method is described that clusters the content of a mixed type document into text or non-text areas. The proposed approach is based on a new set of features combined with a self-organized neural network classifier. The set of features corresponds to the contents and the relationship of 3×3 masks, is selected by using a statistical reduction procedure, and provides texture information. Next, a Principal Components Analyzer (PCA) is applied, which results in a reduced number of `effective' features. The final set of features is then utilized as input vector into a proper neural network to achieve the classification goal. The neural network classifier is based on a Kohonen Self Organized Feature Map (SOFM). Document blocks are classified as text, graphics, and halftones or to secondary subclasses corresponding to special cases of the primal classes. The proposed method can identify text regions included in graphics or even overlapped regions, that is, regions that cannot be separated with horizontal and vertical cuts. The performance of the method was extensively tested on a variety of documents with very promising results.
Url:
DOI: 10.1016/S0262-8856(98)00055-9
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 000698
- to stream Istex, to step Curation: 000690
- to stream Istex, to step Checkpoint: 001593
- to stream Main, to step Merge: 002206
- to stream Main, to step Curation: 002089
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title>Text identification for document image analysis using a neural network</title>
<author><name sortKey="Strouthopoulos, C" sort="Strouthopoulos, C" uniqKey="Strouthopoulos C" first="C." last="Strouthopoulos">C. Strouthopoulos</name>
</author>
<author><name sortKey="Papamarkos, N" sort="Papamarkos, N" uniqKey="Papamarkos N" first="N." last="Papamarkos">N. Papamarkos</name>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">ISTEX</idno>
<idno type="RBID">ISTEX:05D5DC17F8B685775FD1585CF5E87369A05E5E40</idno>
<date when="1998" year="1998">1998</date>
<idno type="doi">10.1016/S0262-8856(98)00055-9</idno>
<idno type="url">https://api.istex.fr/document/05D5DC17F8B685775FD1585CF5E87369A05E5E40/fulltext/pdf</idno>
<idno type="wicri:Area/Istex/Corpus">000698</idno>
<idno type="wicri:Area/Istex/Curation">000690</idno>
<idno type="wicri:Area/Istex/Checkpoint">001593</idno>
<idno type="wicri:doubleKey">0262-8856:1998:Strouthopoulos C:text:identification:for</idno>
<idno type="wicri:Area/Main/Merge">002206</idno>
<idno type="wicri:Area/Main/Curation">002089</idno>
<idno type="wicri:Area/Main/Exploration">002089</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title level="a">Text identification for document image analysis using a neural network</title>
<author><name sortKey="Strouthopoulos, C" sort="Strouthopoulos, C" uniqKey="Strouthopoulos C" first="C." last="Strouthopoulos">C. Strouthopoulos</name>
<affiliation wicri:level="1"><country xml:lang="fr">Grèce</country>
<wicri:regionArea>Electric Circuits Analysis Laboratory, Department of Electrical and Computer Engineering, Democritus University of Thrace, 67100 Xanthi</wicri:regionArea>
<wicri:noRegion>67100 Xanthi</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Papamarkos, N" sort="Papamarkos, N" uniqKey="Papamarkos N" first="N." last="Papamarkos">N. Papamarkos</name>
<affiliation wicri:level="1"><country xml:lang="fr">Grèce</country>
<wicri:regionArea>Electric Circuits Analysis Laboratory, Department of Electrical and Computer Engineering, Democritus University of Thrace, 67100 Xanthi</wicri:regionArea>
<wicri:noRegion>67100 Xanthi</wicri:noRegion>
</affiliation>
</author>
</analytic>
<monogr></monogr>
<series><title level="j">Image and Vision Computing</title>
<title level="j" type="abbrev">IMAVIS</title>
<idno type="ISSN">0262-8856</idno>
<imprint><publisher>ELSEVIER</publisher>
<date type="published" when="1997">1997</date>
<biblScope unit="volume">16</biblScope>
<biblScope unit="issue">12–13</biblScope>
<biblScope unit="page" from="879">879</biblScope>
<biblScope unit="page" to="896">896</biblScope>
</imprint>
<idno type="ISSN">0262-8856</idno>
</series>
<idno type="istex">05D5DC17F8B685775FD1585CF5E87369A05E5E40</idno>
<idno type="DOI">10.1016/S0262-8856(98)00055-9</idno>
<idno type="PII">S0262-8856(98)00055-9</idno>
</biblStruct>
</sourceDesc>
<seriesStmt><idno type="ISSN">0262-8856</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass></textClass>
<langUsage><language ident="en">en</language>
</langUsage>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">A new bottom-up method is described that clusters the content of a mixed type document into text or non-text areas. The proposed approach is based on a new set of features combined with a self-organized neural network classifier. The set of features corresponds to the contents and the relationship of 3×3 masks, is selected by using a statistical reduction procedure, and provides texture information. Next, a Principal Components Analyzer (PCA) is applied, which results in a reduced number of `effective' features. The final set of features is then utilized as input vector into a proper neural network to achieve the classification goal. The neural network classifier is based on a Kohonen Self Organized Feature Map (SOFM). Document blocks are classified as text, graphics, and halftones or to secondary subclasses corresponding to special cases of the primal classes. The proposed method can identify text regions included in graphics or even overlapped regions, that is, regions that cannot be separated with horizontal and vertical cuts. The performance of the method was extensively tested on a variety of documents with very promising results.</div>
</front>
</TEI>
<affiliations><list><country><li>Grèce</li>
</country>
</list>
<tree><country name="Grèce"><noRegion><name sortKey="Strouthopoulos, C" sort="Strouthopoulos, C" uniqKey="Strouthopoulos C" first="C." last="Strouthopoulos">C. Strouthopoulos</name>
</noRegion>
<name sortKey="Papamarkos, N" sort="Papamarkos, N" uniqKey="Papamarkos N" first="N." last="Papamarkos">N. Papamarkos</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 002089 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 002089 | 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:05D5DC17F8B685775FD1585CF5E87369A05E5E40 |texte= Text identification for document image analysis using a neural network }}
This area was generated with Dilib version V0.6.32. |