OcrV1, PascalFrancis, Corpus, bibRecord, 000A47

Character recognition without segmentation

Identifieur interne : 000A47 ( PascalFrancis/Corpus ); précédent : 000A46; suivant : 000A48

Character recognition without segmentation

Auteurs : J. Rocha ; T. Pavlidis

Source :

IEEE Transactions on Pattern Analysis and Machine Intelligence [ 0162-8828 ] ; 1995.

RBID : Pascal:95-0527485

Descripteurs français

Pascal (Inist)
- Application, Algorithme, Système base donnée, Modèle mathématique, Méthode statistique, Processus Markov, Système base connaissances, Reconnaissance caractère, Théorie.

English descriptors

KwdEn :
- Algorithms, Application, Broken character recognition, Character recognition, Character recognition without segmentation, Character segmentation, Database systems, Hidden Markov models, Homeomorphic subgraph matching, Knowledge based systems, Markov processes, Mathematical models, Relative neighborhood graph, Statistical methods, Theory, Touching character recognition.

Abstract

A segmentation-free approach to OCR is presented as part of a knowledge-based word interpretation model. This new method is based on the recognition of subgraphs hemeomorphic to previously defined prototypes of characters. The characters are detected in the order defined by matching quality. Each subgraph that is recognized is introduced as a node in a directed net that compiles different alternative of interpretation of the features in the feature graph. The method allows the recognition of characters that overlap or that are underlined. A final search for the optimal path under certain criteria gives best interpretation of the word features.

Notice en format standard (ISO 2709)

Pour connaître la documentation sur le format Inist Standard.

A01	`01`	`1`		`@0 0162-8828`
A02	`01`			`@0 ITPIDJ`
A03		`1`		`@0 IEEE Trans Pattern Anal Mach Intell`
A05				`@2 17`
A06				`@2 9`
A08	`01`	`1`	`ENG`	`@1 Character recognition without segmentation`
A11	`01`	`1`		`@1 ROCHA (J.)`
A11	`02`	`1`		`@1 PAVLIDIS (T.)`
A14	`01`			`@1 Universitat de les Illes Belears @3 ESP @Z 1 aut.`
A20				`@1 903-909`
A21				`@1 1995`
A23	`01`			`@0 ENG`
A43	`01`			`@1 INIST @2 222 T`
A44				`@0 A100`
A45				`@0 23 Refs.`
A47	`01`	`1`		`@0 95-0527485`
A60				`@1 P`
A61				`@0 A`
A64	`01`	`1`		`@0 IEEE Transactions on Pattern Analysis and Machine Intelligence`
A66	`01`			`@0 USA`
C01	`01`		`ENG`	@0 A segmentation-free approach to OCR is presented as part of a knowledge-based word interpretation model. This new method is based on the recognition of subgraphs hemeomorphic to previously defined prototypes of characters. The characters are detected in the order defined by matching quality. Each subgraph that is recognized is introduced as a node in a directed net that compiles different alternative of interpretation of the features in the feature graph. The method allows the recognition of characters that overlap or that are underlined. A final search for the optimal path under certain criteria gives best interpretation of the word features.
C02	`01`	`1`		`@0 001D02C`
C02	`02`	`1`		`@0 001D02B07D`
C02	`03`	`1`		`@0 001A02I01`
C02	`04`	`1`		`@0 001A02H02`
C02	`05`	`1`		`@0 001A02H01`
C02	`06`	`1`		`@0 001D02C02`
C03	`01`	`1`	`ENG`	`@0 Character recognition without segmentation @4 INC`
C03	`02`	`1`	`ENG`	`@0 Broken character recognition @4 INC`
C03	`03`	`1`	`ENG`	`@0 Touching character recognition @4 INC`
C03	`04`	`1`	`ENG`	`@0 Homeomorphic subgraph matching @4 INC`
C03	`05`	`1`	`ENG`	`@0 Relative neighborhood graph @4 INC`
C03	`06`	`1`	`ENG`	`@0 Character segmentation @4 INC`
C03	`07`	`1`	`ENG`	`@0 Hidden Markov models @4 INC`
C03	`08`	`X`	`FRE`	`@0 Application`
C03	`08`	`X`	`ENG`	`@0 Application`
C03	`08`	`X`	`GER`	`@0 Anwendung`
C03	`08`	`X`	`SPA`	`@0 Aplicación`
C03	`09`	`1`	`FRE`	`@0 Algorithme`
C03	`09`	`1`	`ENG`	`@0 Algorithms`
C03	`10`	`1`	`FRE`	`@0 Système base donnée`
C03	`10`	`1`	`ENG`	`@0 Database systems`
C03	`11`	`1`	`FRE`	`@0 Modèle mathématique`
C03	`11`	`1`	`ENG`	`@0 Mathematical models`
C03	`12`	`1`	`FRE`	`@0 Méthode statistique`
C03	`12`	`1`	`ENG`	`@0 Statistical methods`
C03	`13`	`1`	`FRE`	`@0 Processus Markov`
C03	`13`	`1`	`ENG`	`@0 Markov processes`
C03	`14`	`1`	`FRE`	`@0 Système base connaissances`
C03	`14`	`1`	`ENG`	`@0 Knowledge based systems`
C03	`15`	`1`	`FRE`	`@0 Reconnaissance caractère @3 P`
C03	`15`	`1`	`ENG`	`@0 Character recognition @3 P`
C03	`16`	`1`	`FRE`	`@0 Théorie`
C03	`16`	`1`	`ENG`	`@0 Theory`
N21				`@1 302`

Format Inist (serveur)

NO :	PASCAL 95-0527485 EI
ET :	Character recognition without segmentation
AU :	ROCHA (J.); PAVLIDIS (T.)
AF :	Universitat de les Illes Belears/Espagne (1 aut.)
DT :	Publication en série; Niveau analytique
SO :	IEEE Transactions on Pattern Analysis and Machine Intelligence; ISSN 0162-8828; Coden ITPIDJ; Etats-Unis; Da. 1995; Vol. 17; No. 9; Pp. 903-909; Bibl. 23 Refs.
LA :	Anglais
EA :	A segmentation-free approach to OCR is presented as part of a knowledge-based word interpretation model. This new method is based on the recognition of subgraphs hemeomorphic to previously defined prototypes of characters. The characters are detected in the order defined by matching quality. Each subgraph that is recognized is introduced as a node in a directed net that compiles different alternative of interpretation of the features in the feature graph. The method allows the recognition of characters that overlap or that are underlined. A final search for the optimal path under certain criteria gives best interpretation of the word features.
CC :	001D02C; 001D02B07D; 001A02I01; 001A02H02; 001A02H01; 001D02C02
FD :	Application; Algorithme; Système base donnée; Modèle mathématique; Méthode statistique; Processus Markov; Système base connaissances; Reconnaissance caractère; Théorie
ED :	Character recognition without segmentation; Broken character recognition; Touching character recognition; Homeomorphic subgraph matching; Relative neighborhood graph; Character segmentation; Hidden Markov models; Application; Algorithms; Database systems; Mathematical models; Statistical methods; Markov processes; Knowledge based systems; Character recognition; Theory
GD :	Anwendung
SD :	Aplicación
LO :	INIST-222 T
ID :	95-0527485

Links to Exploration step

Pascal:95-0527485

Le document en format XML

<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Character recognition without segmentation</title>
<author><name sortKey="Rocha, J" sort="Rocha, J" uniqKey="Rocha J" first="J." last="Rocha">J. Rocha</name>
<affiliation><inist:fA14 i1="01"><s1>Universitat de les Illes Belears</s1>
<s3>ESP</s3>
<sZ>1 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Pavlidis, T" sort="Pavlidis, T" uniqKey="Pavlidis T" first="T." last="Pavlidis">T. Pavlidis</name>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">95-0527485</idno>
<date when="1995">1995</date>
<idno type="stanalyst">PASCAL 95-0527485 EI</idno>
<idno type="RBID">Pascal:95-0527485</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000A47</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Character recognition without segmentation</title>
<author><name sortKey="Rocha, J" sort="Rocha, J" uniqKey="Rocha J" first="J." last="Rocha">J. Rocha</name>
<affiliation><inist:fA14 i1="01"><s1>Universitat de les Illes Belears</s1>
<s3>ESP</s3>
<sZ>1 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Pavlidis, T" sort="Pavlidis, T" uniqKey="Pavlidis T" first="T." last="Pavlidis">T. Pavlidis</name>
</author>
</analytic>
<series><title level="j" type="main">IEEE Transactions on Pattern Analysis and Machine Intelligence</title>
<title level="j" type="abbreviated">IEEE Trans Pattern Anal Mach Intell</title>
<idno type="ISSN">0162-8828</idno>
<imprint><date when="1995">1995</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><title level="j" type="main">IEEE Transactions on Pattern Analysis and Machine Intelligence</title>
<title level="j" type="abbreviated">IEEE Trans Pattern Anal Mach Intell</title>
<idno type="ISSN">0162-8828</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Algorithms</term>
<term>Application</term>
<term>Broken character recognition</term>
<term>Character recognition</term>
<term>Character recognition without segmentation</term>
<term>Character segmentation</term>
<term>Database systems</term>
<term>Hidden Markov models</term>
<term>Homeomorphic subgraph matching</term>
<term>Knowledge based systems</term>
<term>Markov processes</term>
<term>Mathematical models</term>
<term>Relative neighborhood graph</term>
<term>Statistical methods</term>
<term>Theory</term>
<term>Touching character recognition</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Application</term>
<term>Algorithme</term>
<term>Système base donnée</term>
<term>Modèle mathématique</term>
<term>Méthode statistique</term>
<term>Processus Markov</term>
<term>Système base connaissances</term>
<term>Reconnaissance caractère</term>
<term>Théorie</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">A segmentation-free approach to OCR is presented as part of a knowledge-based  word interpretation model.  This new method is based on the recognition of subgraphs hemeomorphic to previously defined prototypes of characters.  The characters are detected in the order defined by matching quality.  Each subgraph that is recognized is introduced as a node in a directed net that compiles different alternative of interpretation of the features in the feature graph. The method allows the recognition of characters that overlap or that are underlined.  A final search for the optimal path under certain criteria gives best interpretation of the word features.</div>
</front>
</TEI>
<inist><standard h6="B"><pA><fA01 i1="01" i2="1"><s0>0162-8828</s0>
</fA01>
<fA02 i1="01"><s0>ITPIDJ</s0>
</fA02>
<fA03 i2="1"><s0>IEEE Trans Pattern Anal Mach Intell</s0>
</fA03>
<fA05><s2>17</s2>
</fA05>
<fA06><s2>9</s2>
</fA06>
<fA08 i1="01" i2="1" l="ENG"><s1>Character recognition without segmentation</s1>
</fA08>
<fA11 i1="01" i2="1"><s1>ROCHA (J.)</s1>
</fA11>
<fA11 i1="02" i2="1"><s1>PAVLIDIS (T.)</s1>
</fA11>
<fA14 i1="01"><s1>Universitat de les Illes Belears</s1>
<s3>ESP</s3>
<sZ>1 aut.</sZ>
</fA14>
<fA20><s1>903-909</s1>
</fA20>
<fA21><s1>1995</s1>
</fA21>
<fA23 i1="01"><s0>ENG</s0>
</fA23>
<fA43 i1="01"><s1>INIST</s1>
<s2>222 T</s2>
</fA43>
<fA44><s0>A100</s0>
</fA44>
<fA45><s0>23 Refs.</s0>
</fA45>
<fA47 i1="01" i2="1"><s0>95-0527485</s0>
</fA47>
<fA60><s1>P</s1>
</fA60>
<fA61><s0>A</s0>
</fA61>
<fA64 i1="01" i2="1"><s0>IEEE Transactions on Pattern Analysis and Machine Intelligence</s0>
</fA64>
<fA66 i1="01"><s0>USA</s0>
</fA66>
<fC01 i1="01" l="ENG"><s0>A segmentation-free approach to OCR is presented as part of a knowledge-based  word interpretation model.  This new method is based on the recognition of subgraphs hemeomorphic to previously defined prototypes of characters.  The characters are detected in the order defined by matching quality.  Each subgraph that is recognized is introduced as a node in a directed net that compiles different alternative of interpretation of the features in the feature graph. The method allows the recognition of characters that overlap or that are underlined.  A final search for the optimal path under certain criteria gives best interpretation of the word features.</s0>
</fC01>
<fC02 i1="01" i2="1"><s0>001D02C</s0>
</fC02>
<fC02 i1="02" i2="1"><s0>001D02B07D</s0>
</fC02>
<fC02 i1="03" i2="1"><s0>001A02I01</s0>
</fC02>
<fC02 i1="04" i2="1"><s0>001A02H02</s0>
</fC02>
<fC02 i1="05" i2="1"><s0>001A02H01</s0>
</fC02>
<fC02 i1="06" i2="1"><s0>001D02C02</s0>
</fC02>
<fC03 i1="01" i2="1" l="ENG"><s0>Character recognition without segmentation</s0>
<s4>INC</s4>
</fC03>
<fC03 i1="02" i2="1" l="ENG"><s0>Broken character recognition</s0>
<s4>INC</s4>
</fC03>
<fC03 i1="03" i2="1" l="ENG"><s0>Touching character recognition</s0>
<s4>INC</s4>
</fC03>
<fC03 i1="04" i2="1" l="ENG"><s0>Homeomorphic subgraph matching</s0>
<s4>INC</s4>
</fC03>
<fC03 i1="05" i2="1" l="ENG"><s0>Relative neighborhood graph</s0>
<s4>INC</s4>
</fC03>
<fC03 i1="06" i2="1" l="ENG"><s0>Character segmentation</s0>
<s4>INC</s4>
</fC03>
<fC03 i1="07" i2="1" l="ENG"><s0>Hidden Markov models</s0>
<s4>INC</s4>
</fC03>
<fC03 i1="08" i2="X" l="FRE"><s0>Application</s0>
</fC03>
<fC03 i1="08" i2="X" l="ENG"><s0>Application</s0>
</fC03>
<fC03 i1="08" i2="X" l="GER"><s0>Anwendung</s0>
</fC03>
<fC03 i1="08" i2="X" l="SPA"><s0>Aplicación</s0>
</fC03>
<fC03 i1="09" i2="1" l="FRE"><s0>Algorithme</s0>
</fC03>
<fC03 i1="09" i2="1" l="ENG"><s0>Algorithms</s0>
</fC03>
<fC03 i1="10" i2="1" l="FRE"><s0>Système base donnée</s0>
</fC03>
<fC03 i1="10" i2="1" l="ENG"><s0>Database systems</s0>
</fC03>
<fC03 i1="11" i2="1" l="FRE"><s0>Modèle mathématique</s0>
</fC03>
<fC03 i1="11" i2="1" l="ENG"><s0>Mathematical models</s0>
</fC03>
<fC03 i1="12" i2="1" l="FRE"><s0>Méthode statistique</s0>
</fC03>
<fC03 i1="12" i2="1" l="ENG"><s0>Statistical methods</s0>
</fC03>
<fC03 i1="13" i2="1" l="FRE"><s0>Processus Markov</s0>
</fC03>
<fC03 i1="13" i2="1" l="ENG"><s0>Markov processes</s0>
</fC03>
<fC03 i1="14" i2="1" l="FRE"><s0>Système base connaissances</s0>
</fC03>
<fC03 i1="14" i2="1" l="ENG"><s0>Knowledge based systems</s0>
</fC03>
<fC03 i1="15" i2="1" l="FRE"><s0>Reconnaissance caractère</s0>
<s3>P</s3>
</fC03>
<fC03 i1="15" i2="1" l="ENG"><s0>Character recognition</s0>
<s3>P</s3>
</fC03>
<fC03 i1="16" i2="1" l="FRE"><s0>Théorie</s0>
</fC03>
<fC03 i1="16" i2="1" l="ENG"><s0>Theory</s0>
</fC03>
<fN21><s1>302</s1>
</fN21>
</pA>
</standard>
<server><NO>PASCAL 95-0527485 EI</NO>
<ET>Character recognition without segmentation</ET>
<AU>ROCHA (J.); PAVLIDIS (T.)</AU>
<AF>Universitat de les Illes Belears/Espagne (1 aut.)</AF>
<DT>Publication en série; Niveau analytique</DT>
<SO>IEEE Transactions on Pattern Analysis and Machine Intelligence; ISSN 0162-8828; Coden ITPIDJ; Etats-Unis; Da. 1995; Vol. 17; No. 9; Pp. 903-909; Bibl. 23 Refs.</SO>
<LA>Anglais</LA>
<EA>A segmentation-free approach to OCR is presented as part of a knowledge-based  word interpretation model.  This new method is based on the recognition of subgraphs hemeomorphic to previously defined prototypes of characters.  The characters are detected in the order defined by matching quality.  Each subgraph that is recognized is introduced as a node in a directed net that compiles different alternative of interpretation of the features in the feature graph. The method allows the recognition of characters that overlap or that are underlined.  A final search for the optimal path under certain criteria gives best interpretation of the word features.</EA>
<CC>001D02C; 001D02B07D; 001A02I01; 001A02H02; 001A02H01; 001D02C02</CC>
<FD>Application; Algorithme; Système base donnée; Modèle mathématique; Méthode statistique; Processus Markov; Système base connaissances; Reconnaissance caractère; Théorie</FD>
<ED>Character recognition without segmentation; Broken character recognition; Touching character recognition; Homeomorphic subgraph matching; Relative neighborhood graph; Character segmentation; Hidden Markov models; Application; Algorithms; Database systems; Mathematical models; Statistical methods; Markov processes; Knowledge based systems; Character recognition; Theory</ED>
<GD>Anwendung</GD>
<SD>Aplicación</SD>
<LO>INIST-222 T</LO>
<ID>95-0527485</ID>
</server>
</inist>
</record>

Pour manipuler ce document sous Unix (Dilib)

EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/PascalFrancis/Corpus

HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000A47 | SxmlIndent | more

HfdSelect -h $EXPLOR_AREA/Data/PascalFrancis/Corpus/biblio.hfd -nk 000A47 | SxmlIndent | more

Pour mettre un lien sur cette page dans le réseau Wicri

{{Explor lien
   |wiki=    Ticri/CIDE
   |area=    OcrV1
   |flux=    PascalFrancis
   |étape=   Corpus
   |type=    RBID
   |clé=     Pascal:95-0527485
   |texte=   Character recognition without segmentation
}}

This area was generated with Dilib version V0.6.32.
Data generation: Sat Nov 11 16:53:45 2017. Site generation: Mon Mar 11 23:15:16 2024

	Serveur d'exploration sur l'OCR
	Attention, ce site est en cours de développement ! Attention, site généré par des moyens informatiques à partir de corpus bruts. Les informations ne sont donc pas validées.

Serveur d'exploration sur l'OCR

Character recognition without segmentation

Character recognition without segmentation

Source :

Descripteurs français

English descriptors

Abstract

Notice en format standard (ISO 2709)

Format Inist (serveur)

Links to Exploration step

Le document en format XML

Pour manipuler ce document sous Unix (Dilib)

Pour mettre un lien sur cette page dans le réseau Wicri