A Model-based System for the Recognition of Structured Documents
Identifieur interne : 000B95 ( Crin/Corpus ); précédent : 000B94; suivant : 000B96A Model-based System for the Recognition of Structured Documents
Auteurs : Y. Chenevoy ; A. Belaïd ; O. T AkindeleSource :
English descriptors
Abstract
This paper describes a document recognition system (GRAPHEIN) that is based on the exploitation of the inherent knowledge in the structure of the document to be treated and in the language in which it is written. It is implemented using a blackboard architecture which is a form of knowledge based problem-solving model capable of handling multiple cooperating knowledge sources. The model is composed of information about the document structure and about the characteristics of its contents. The document structure is defined with the aid of an ODA-like formalism that characterizes the composition and occurrences of different physico-logical objects of the document. Document analysis and recognition are based on generation and management of hypotheses, which determine the adopted processing strategy. When the hypotheses are sure enough, a top-down strategy guided by the model is applied. In case of doubt, a mixed strategy that extracts clues from the image is used. On the other hand, a bottom-up strategy (fusion process) is activated when the model is not directly usable.
Links to Exploration step
CRIN:chenevoy91bLe document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" wicri:score="182">A Model-based System for the Recognition of Structured Documents</title>
</titleStmt>
<publicationStmt><idno type="RBID">CRIN:chenevoy91b</idno>
<date when="1991" year="1991">1991</date>
<idno type="wicri:Area/Crin/Corpus">000B95</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en">A Model-based System for the Recognition of Structured Documents</title>
<author><name sortKey="Chenevoy, Y" sort="Chenevoy, Y" uniqKey="Chenevoy Y" first="Y." last="Chenevoy">Y. Chenevoy</name>
</author>
<author><name sortKey="Belaid, A" sort="Belaid, A" uniqKey="Belaid A" first="A." last="Belaïd">A. Belaïd</name>
</author>
<author><name sortKey="Akindele, O T" sort="Akindele, O T" uniqKey="Akindele O" first="O. T" last="Akindele">O. T Akindele</name>
</author>
</analytic>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>ODA</term>
<term>blackboard architecture</term>
<term>document structure analysis</term>
<term>hypotheses management</term>
<term>model</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en" wicri:score="3171">This paper describes a document recognition system (GRAPHEIN) that is based on the exploitation of the inherent knowledge in the structure of the document to be treated and in the language in which it is written. It is implemented using a blackboard architecture which is a form of knowledge based problem-solving model capable of handling multiple cooperating knowledge sources. The model is composed of information about the document structure and about the characteristics of its contents. The document structure is defined with the aid of an ODA-like formalism that characterizes the composition and occurrences of different physico-logical objects of the document. Document analysis and recognition are based on generation and management of hypotheses, which determine the adopted processing strategy. When the hypotheses are sure enough, a top-down strategy guided by the model is applied. In case of doubt, a mixed strategy that extracts clues from the image is used. On the other hand, a bottom-up strategy (fusion process) is activated when the model is not directly usable.</div>
</front>
</TEI>
<BibTex type="techreport"><ref>chenevoy91b</ref>
<crinnumber>91-R-126</crinnumber>
<category>15</category>
<equipe>RFIA</equipe>
<author><e>Chenevoy, Y.</e>
<e>Belaïd, A.</e>
<e>Akindele, O.T</e>
</author>
<title>A Model-based System for the Recognition of Structured Documents</title>
<institution>Centre de Recherche en Informatique de Nancy</institution>
<year>1991</year>
<type>Rapport interne</type>
<address>Vandoeuvre-lès-Nancy</address>
<note>submitted to IEEE Computers</note>
<keywords><e>document structure analysis</e>
<e>model</e>
<e>hypotheses management</e>
<e>ODA</e>
<e>blackboard architecture</e>
</keywords>
<abstract>This paper describes a document recognition system (GRAPHEIN) that is based on the exploitation of the inherent knowledge in the structure of the document to be treated and in the language in which it is written. It is implemented using a blackboard architecture which is a form of knowledge based problem-solving model capable of handling multiple cooperating knowledge sources. The model is composed of information about the document structure and about the characteristics of its contents. The document structure is defined with the aid of an ODA-like formalism that characterizes the composition and occurrences of different physico-logical objects of the document. Document analysis and recognition are based on generation and management of hypotheses, which determine the adopted processing strategy. When the hypotheses are sure enough, a top-down strategy guided by the model is applied. In case of doubt, a mixed strategy that extracts clues from the image is used. On the other hand, a bottom-up strategy (fusion process) is activated when the model is not directly usable.</abstract>
</BibTex>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/Crin/Corpus
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000B95 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Crin/Corpus/biblio.hfd -nk 000B95 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Wicri/Lorraine |area= InforLorV4 |flux= Crin |étape= Corpus |type= RBID |clé= CRIN:chenevoy91b |texte= A Model-based System for the Recognition of Structured Documents }}
![]() | This area was generated with Dilib version V0.6.33. | ![]() |