OcrV1, PascalFrancis, Corpus, bibRecord, 000A31

A novel architecture for high quality hand-printed character recognition

Identifieur interne : 000A31 ( PascalFrancis/Corpus ); précédent : 000A30; suivant : 000A32

A novel architecture for high quality hand-printed character recognition

Auteurs : Z. M. Kovacs-V.

Source :

Pattern recognition [ 0031-3203 ] ; 1995.

RBID : Pascal:96-0026739

Descripteurs français

Pascal (Inist)
- Reconnaissance caractère, Caractère imprimé, Caractère manuscrit, Classificateur, Classification, Taux erreur, Base donnée, Réseau neuronal, OCR, MLP.

English descriptors

KwdEn :
- Character recognition, Classification, Classifier, Database, Error rate, MLP, Manuscript character, Neural network, OCR, Printed character.

Abstract

A new architecture for statistical classification of hand-printed characters is presented. It is based on standard preprocessing and three feature types, containing geometrical information on the position of the pixels, on the contour orientation and on the bending points, respectively. Two feature vectors at a time are used as inputs to a multi-layer perceptron-based classifier, giving rise to three simple classifiers operating in parallel. The outputs of the three different classifiers are mixed by a final supervisor realized by a perceptron layer. The overall network has been trained using digits, upper and lower case letters of the NIST Special Database 3. Classification results of the NIST Test Data 1 are provided. The system has an error rate of 2.59% on the digits of NIST Test Data 1 at zero rejection rate, while it has 2.99 and 11.00% error rate on the upper and lower case letters, respectively.

Notice en format standard (ISO 2709)

Pour connaître la documentation sur le format Inist Standard.

A01	`01`	`1`		`@0 0031-3203`
A02	`01`			`@0 PTNRA8`
A03		`1`		`@0 Pattern recogn.`
A05				`@2 28`
A06				`@2 11`
A08	`01`	`1`	`ENG`	`@1 A novel architecture for high quality hand-printed character recognition`
A11	`01`	`1`		`@1 KOVACS-V. (Z. M.)`
A14	`01`			`@1 Univ. Bologna, dip. elettronica informatica sistemistica @2 40136 Bologna @3 ITA`
A20				`@1 1685-1692`
A21				`@1 1995`
A23	`01`			`@0 ENG`
A43	`01`			`@1 INIST @2 15220 @5 354000058958920050`
A44				`@0 0000`
A45				`@0 20 ref.`
A47	`01`	`1`		`@0 96-0026739`
A60				`@1 P`
A61				`@0 A`
A64	`01`	`1`		`@0 Pattern recognition`
A66	`01`			`@0 GBR`
C01	`01`		`ENG`	@0 A new architecture for statistical classification of hand-printed characters is presented. It is based on standard preprocessing and three feature types, containing geometrical information on the position of the pixels, on the contour orientation and on the bending points, respectively. Two feature vectors at a time are used as inputs to a multi-layer perceptron-based classifier, giving rise to three simple classifiers operating in parallel. The outputs of the three different classifiers are mixed by a final supervisor realized by a perceptron layer. The overall network has been trained using digits, upper and lower case letters of the NIST Special Database 3. Classification results of the NIST Test Data 1 are provided. The system has an error rate of 2.59% on the digits of NIST Test Data 1 at zero rejection rate, while it has 2.99 and 11.00% error rate on the upper and lower case letters, respectively.
C02	`01`	`X`		`@0 001D02C03`
C02	`02`	`X`		`@0 001D02C06`
C03	`01`	`X`	`FRE`	`@0 Reconnaissance caractère @5 01`
C03	`01`	`X`	`ENG`	`@0 Character recognition @5 01`
C03	`01`	`X`	`SPA`	`@0 Reconocimiento carácter @5 01`
C03	`02`	`X`	`FRE`	`@0 Caractère imprimé @5 02`
C03	`02`	`X`	`ENG`	`@0 Printed character @5 02`
C03	`02`	`X`	`SPA`	`@0 Carácter impreso @5 02`
C03	`03`	`X`	`FRE`	`@0 Caractère manuscrit @5 03`
C03	`03`	`X`	`ENG`	`@0 Manuscript character @5 03`
C03	`03`	`X`	`SPA`	`@0 Carácter manuscrito @5 03`
C03	`04`	`X`	`FRE`	`@0 Classificateur @5 04`
C03	`04`	`X`	`ENG`	`@0 Classifier @5 04`
C03	`04`	`X`	`SPA`	`@0 Clasificador @5 04`
C03	`05`	`X`	`FRE`	`@0 Classification @5 05`
C03	`05`	`X`	`ENG`	`@0 Classification @5 05`
C03	`05`	`X`	`GER`	`@0 Klassifizierung @5 05`
C03	`05`	`X`	`SPA`	`@0 Clasificación @5 05`
C03	`06`	`X`	`FRE`	`@0 Taux erreur @5 06`
C03	`06`	`X`	`ENG`	`@0 Error rate @5 06`
C03	`06`	`X`	`SPA`	`@0 Indice error @5 06`
C03	`07`	`X`	`FRE`	`@0 Base donnée @5 07`
C03	`07`	`X`	`ENG`	`@0 Database @5 07`
C03	`07`	`X`	`SPA`	`@0 Base dato @5 07`
C03	`08`	`X`	`FRE`	`@0 Réseau neuronal @5 08`
C03	`08`	`X`	`ENG`	`@0 Neural network @5 08`
C03	`08`	`X`	`SPA`	`@0 Red neuronal @5 08`
C03	`09`	`X`	`FRE`	`@0 OCR @4 CD @5 96`
C03	`09`	`X`	`ENG`	`@0 OCR @4 CD @5 96`
C03	`10`	`X`	`FRE`	`@0 MLP @4 CD @5 97`
C03	`10`	`X`	`ENG`	`@0 MLP @4 CD @5 97`
N21				`@1 001`

Format Inist (serveur)

NO :	PASCAL 96-0026739 INIST
ET :	A novel architecture for high quality hand-printed character recognition
AU :	KOVACS-V. (Z. M.)
AF :	Univ. Bologna, dip. elettronica informatica sistemistica/40136 Bologna/Italie
DT :	Publication en série; Niveau analytique
SO :	Pattern recognition; ISSN 0031-3203; Coden PTNRA8; Royaume-Uni; Da. 1995; Vol. 28; No. 11; Pp. 1685-1692; Bibl. 20 ref.
LA :	Anglais
EA :	A new architecture for statistical classification of hand-printed characters is presented. It is based on standard preprocessing and three feature types, containing geometrical information on the position of the pixels, on the contour orientation and on the bending points, respectively. Two feature vectors at a time are used as inputs to a multi-layer perceptron-based classifier, giving rise to three simple classifiers operating in parallel. The outputs of the three different classifiers are mixed by a final supervisor realized by a perceptron layer. The overall network has been trained using digits, upper and lower case letters of the NIST Special Database 3. Classification results of the NIST Test Data 1 are provided. The system has an error rate of 2.59% on the digits of NIST Test Data 1 at zero rejection rate, while it has 2.99 and 11.00% error rate on the upper and lower case letters, respectively.
CC :	001D02C03; 001D02C06
FD :	Reconnaissance caractère; Caractère imprimé; Caractère manuscrit; Classificateur; Classification; Taux erreur; Base donnée; Réseau neuronal; OCR; MLP
ED :	Character recognition; Printed character; Manuscript character; Classifier; Classification; Error rate; Database; Neural network; OCR; MLP
GD :	Klassifizierung
SD :	Reconocimiento carácter; Carácter impreso; Carácter manuscrito; Clasificador; Clasificación; Indice error; Base dato; Red neuronal
LO :	INIST-15220.354000058958920050
ID :	96-0026739

Links to Exploration step

Pascal:96-0026739

Le document en format XML

<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">A novel architecture for high quality hand-printed character recognition</title>
<author><name sortKey="Kovacs V, Z M" sort="Kovacs V, Z M" uniqKey="Kovacs V Z" first="Z. M." last="Kovacs-V.">Z. M. Kovacs-V.</name>
<affiliation><inist:fA14 i1="01"><s1>Univ. Bologna, dip. elettronica informatica sistemistica</s1>
<s2>40136 Bologna</s2>
<s3>ITA</s3>
</inist:fA14>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">96-0026739</idno>
<date when="1995">1995</date>
<idno type="stanalyst">PASCAL 96-0026739 INIST</idno>
<idno type="RBID">Pascal:96-0026739</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000A31</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">A novel architecture for high quality hand-printed character recognition</title>
<author><name sortKey="Kovacs V, Z M" sort="Kovacs V, Z M" uniqKey="Kovacs V Z" first="Z. M." last="Kovacs-V.">Z. M. Kovacs-V.</name>
<affiliation><inist:fA14 i1="01"><s1>Univ. Bologna, dip. elettronica informatica sistemistica</s1>
<s2>40136 Bologna</s2>
<s3>ITA</s3>
</inist:fA14>
</affiliation>
</author>
</analytic>
<series><title level="j" type="main">Pattern recognition</title>
<title level="j" type="abbreviated">Pattern recogn.</title>
<idno type="ISSN">0031-3203</idno>
<imprint><date when="1995">1995</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><title level="j" type="main">Pattern recognition</title>
<title level="j" type="abbreviated">Pattern recogn.</title>
<idno type="ISSN">0031-3203</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Character recognition</term>
<term>Classification</term>
<term>Classifier</term>
<term>Database</term>
<term>Error rate</term>
<term>MLP</term>
<term>Manuscript character</term>
<term>Neural network</term>
<term>OCR</term>
<term>Printed character</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Reconnaissance caractère</term>
<term>Caractère imprimé</term>
<term>Caractère manuscrit</term>
<term>Classificateur</term>
<term>Classification</term>
<term>Taux erreur</term>
<term>Base donnée</term>
<term>Réseau neuronal</term>
<term>OCR</term>
<term>MLP</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">A new architecture for statistical classification of hand-printed characters is presented. It is based on standard preprocessing and three feature types, containing geometrical information on the position of the pixels, on the contour orientation and on the bending points, respectively. Two feature vectors at a time are used as inputs to a multi-layer perceptron-based classifier, giving rise to three simple classifiers operating in parallel. The outputs of the three different classifiers are mixed by a final supervisor realized by a perceptron layer. The overall network has been trained using digits, upper and lower case letters of the NIST Special Database 3. Classification results of the NIST Test Data 1 are provided. The system has an error rate of 2.59% on the digits of NIST Test Data 1 at zero rejection rate, while it has 2.99 and 11.00% error rate on the upper and lower case letters, respectively.</div>
</front>
</TEI>
<inist><standard h6="B"><pA><fA01 i1="01" i2="1"><s0>0031-3203</s0>
</fA01>
<fA02 i1="01"><s0>PTNRA8</s0>
</fA02>
<fA03 i2="1"><s0>Pattern recogn.</s0>
</fA03>
<fA05><s2>28</s2>
</fA05>
<fA06><s2>11</s2>
</fA06>
<fA08 i1="01" i2="1" l="ENG"><s1>A novel architecture for high quality hand-printed character recognition</s1>
</fA08>
<fA11 i1="01" i2="1"><s1>KOVACS-V. (Z. M.)</s1>
</fA11>
<fA14 i1="01"><s1>Univ. Bologna, dip. elettronica informatica sistemistica</s1>
<s2>40136 Bologna</s2>
<s3>ITA</s3>
</fA14>
<fA20><s1>1685-1692</s1>
</fA20>
<fA21><s1>1995</s1>
</fA21>
<fA23 i1="01"><s0>ENG</s0>
</fA23>
<fA43 i1="01"><s1>INIST</s1>
<s2>15220</s2>
<s5>354000058958920050</s5>
</fA43>
<fA44><s0>0000</s0>
</fA44>
<fA45><s0>20 ref.</s0>
</fA45>
<fA47 i1="01" i2="1"><s0>96-0026739</s0>
</fA47>
<fA60><s1>P</s1>
</fA60>
<fA61><s0>A</s0>
</fA61>
<fA64 i1="01" i2="1"><s0>Pattern recognition</s0>
</fA64>
<fA66 i1="01"><s0>GBR</s0>
</fA66>
<fC01 i1="01" l="ENG"><s0>A new architecture for statistical classification of hand-printed characters is presented. It is based on standard preprocessing and three feature types, containing geometrical information on the position of the pixels, on the contour orientation and on the bending points, respectively. Two feature vectors at a time are used as inputs to a multi-layer perceptron-based classifier, giving rise to three simple classifiers operating in parallel. The outputs of the three different classifiers are mixed by a final supervisor realized by a perceptron layer. The overall network has been trained using digits, upper and lower case letters of the NIST Special Database 3. Classification results of the NIST Test Data 1 are provided. The system has an error rate of 2.59% on the digits of NIST Test Data 1 at zero rejection rate, while it has 2.99 and 11.00% error rate on the upper and lower case letters, respectively.</s0>
</fC01>
<fC02 i1="01" i2="X"><s0>001D02C03</s0>
</fC02>
<fC02 i1="02" i2="X"><s0>001D02C06</s0>
</fC02>
<fC03 i1="01" i2="X" l="FRE"><s0>Reconnaissance caractère</s0>
<s5>01</s5>
</fC03>
<fC03 i1="01" i2="X" l="ENG"><s0>Character recognition</s0>
<s5>01</s5>
</fC03>
<fC03 i1="01" i2="X" l="SPA"><s0>Reconocimiento carácter</s0>
<s5>01</s5>
</fC03>
<fC03 i1="02" i2="X" l="FRE"><s0>Caractère imprimé</s0>
<s5>02</s5>
</fC03>
<fC03 i1="02" i2="X" l="ENG"><s0>Printed character</s0>
<s5>02</s5>
</fC03>
<fC03 i1="02" i2="X" l="SPA"><s0>Carácter impreso</s0>
<s5>02</s5>
</fC03>
<fC03 i1="03" i2="X" l="FRE"><s0>Caractère manuscrit</s0>
<s5>03</s5>
</fC03>
<fC03 i1="03" i2="X" l="ENG"><s0>Manuscript character</s0>
<s5>03</s5>
</fC03>
<fC03 i1="03" i2="X" l="SPA"><s0>Carácter manuscrito</s0>
<s5>03</s5>
</fC03>
<fC03 i1="04" i2="X" l="FRE"><s0>Classificateur</s0>
<s5>04</s5>
</fC03>
<fC03 i1="04" i2="X" l="ENG"><s0>Classifier</s0>
<s5>04</s5>
</fC03>
<fC03 i1="04" i2="X" l="SPA"><s0>Clasificador</s0>
<s5>04</s5>
</fC03>
<fC03 i1="05" i2="X" l="FRE"><s0>Classification</s0>
<s5>05</s5>
</fC03>
<fC03 i1="05" i2="X" l="ENG"><s0>Classification</s0>
<s5>05</s5>
</fC03>
<fC03 i1="05" i2="X" l="GER"><s0>Klassifizierung</s0>
<s5>05</s5>
</fC03>
<fC03 i1="05" i2="X" l="SPA"><s0>Clasificación</s0>
<s5>05</s5>
</fC03>
<fC03 i1="06" i2="X" l="FRE"><s0>Taux erreur</s0>
<s5>06</s5>
</fC03>
<fC03 i1="06" i2="X" l="ENG"><s0>Error rate</s0>
<s5>06</s5>
</fC03>
<fC03 i1="06" i2="X" l="SPA"><s0>Indice error</s0>
<s5>06</s5>
</fC03>
<fC03 i1="07" i2="X" l="FRE"><s0>Base donnée</s0>
<s5>07</s5>
</fC03>
<fC03 i1="07" i2="X" l="ENG"><s0>Database</s0>
<s5>07</s5>
</fC03>
<fC03 i1="07" i2="X" l="SPA"><s0>Base dato</s0>
<s5>07</s5>
</fC03>
<fC03 i1="08" i2="X" l="FRE"><s0>Réseau neuronal</s0>
<s5>08</s5>
</fC03>
<fC03 i1="08" i2="X" l="ENG"><s0>Neural network</s0>
<s5>08</s5>
</fC03>
<fC03 i1="08" i2="X" l="SPA"><s0>Red neuronal</s0>
<s5>08</s5>
</fC03>
<fC03 i1="09" i2="X" l="FRE"><s0>OCR</s0>
<s4>CD</s4>
<s5>96</s5>
</fC03>
<fC03 i1="09" i2="X" l="ENG"><s0>OCR</s0>
<s4>CD</s4>
<s5>96</s5>
</fC03>
<fC03 i1="10" i2="X" l="FRE"><s0>MLP</s0>
<s4>CD</s4>
<s5>97</s5>
</fC03>
<fC03 i1="10" i2="X" l="ENG"><s0>MLP</s0>
<s4>CD</s4>
<s5>97</s5>
</fC03>
<fN21><s1>001</s1>
</fN21>
</pA>
</standard>
<server><NO>PASCAL 96-0026739 INIST</NO>
<ET>A novel architecture for high quality hand-printed character recognition</ET>
<AU>KOVACS-V. (Z. M.)</AU>
<AF>Univ. Bologna, dip. elettronica informatica sistemistica/40136 Bologna/Italie</AF>
<DT>Publication en série; Niveau analytique</DT>
<SO>Pattern recognition; ISSN 0031-3203; Coden PTNRA8; Royaume-Uni; Da. 1995; Vol. 28; No. 11; Pp. 1685-1692; Bibl. 20 ref.</SO>
<LA>Anglais</LA>
<EA>A new architecture for statistical classification of hand-printed characters is presented. It is based on standard preprocessing and three feature types, containing geometrical information on the position of the pixels, on the contour orientation and on the bending points, respectively. Two feature vectors at a time are used as inputs to a multi-layer perceptron-based classifier, giving rise to three simple classifiers operating in parallel. The outputs of the three different classifiers are mixed by a final supervisor realized by a perceptron layer. The overall network has been trained using digits, upper and lower case letters of the NIST Special Database 3. Classification results of the NIST Test Data 1 are provided. The system has an error rate of 2.59% on the digits of NIST Test Data 1 at zero rejection rate, while it has 2.99 and 11.00% error rate on the upper and lower case letters, respectively.</EA>
<CC>001D02C03; 001D02C06</CC>
<FD>Reconnaissance caractère; Caractère imprimé; Caractère manuscrit; Classificateur; Classification; Taux erreur; Base donnée; Réseau neuronal; OCR; MLP</FD>
<ED>Character recognition; Printed character; Manuscript character; Classifier; Classification; Error rate; Database; Neural network; OCR; MLP</ED>
<GD>Klassifizierung</GD>
<SD>Reconocimiento carácter; Carácter impreso; Carácter manuscrito; Clasificador; Clasificación; Indice error; Base dato; Red neuronal</SD>
<LO>INIST-15220.354000058958920050</LO>
<ID>96-0026739</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 000A31 | SxmlIndent | more

HfdSelect -h $EXPLOR_AREA/Data/PascalFrancis/Corpus/biblio.hfd -nk 000A31 | 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:96-0026739
   |texte=   A novel architecture for high quality hand-printed character recognition
}}

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

A novel architecture for high quality hand-printed character recognition

A novel architecture for high quality hand-printed character recognition

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