A new cost function for typewritten digits segmentation
Identifieur interne :
000854 ( PascalFrancis/Corpus );
précédent :
000853;
suivant :
000855
A new cost function for typewritten digits segmentation
Auteurs : C. Rodriguez ;
J. Muguerza ;
M. Navarro ;
A. Zarate ;
J. I. Martin ;
J. M. PerezSource :
-
Lecture notes in computer science [ 0302-9743 ] ; 1998.
RBID : Pascal:98-0504545
Descripteurs français
English descriptors
Abstract
This work presents a solution to the problem of the segmentation of digits in forms characterized by its low quality, as well as the existence of breaks and touching digits. We propose a new function of segmentation that adds to two traditional techniques (vertical projections and Tsujimoto metric) information of background of the digit. Unlike other techniques reported in the literature, ours obtains a near-optimum number of break points in fields containing broken, blurred and touching characters, leading to high accuracy in the global OCR system. The accuracy obtained in the segmentation of the forms fields is of 99,74% on a sample of 11,283 fields of 144 forms of low quality, which provides a final accuracy to the automatic recognition process of 99.42% of digits correctly classified.
Notice en format standard (ISO 2709)
Pour connaître la documentation sur le format Inist Standard.
| pA |
| A01 | 01 | 1 | | @0 0302-9743 |
|---|
| A05 | | | | @2 1451 |
|---|
| A08 | 01 | 1 | ENG | @1 A new cost function for typewritten digits segmentation |
|---|
| A09 | 01 | 1 | ENG | @1 Advances in pattern recognition : Sydney, 11-13 August 1998 |
|---|
| A11 | 01 | 1 | | @1 RODRIGUEZ (C.) |
|---|
| A11 | 02 | 1 | | @1 MUGUERZA (J.) |
|---|
| A11 | 03 | 1 | | @1 NAVARRO (M.) |
|---|
| A11 | 04 | 1 | | @1 ZARATE (A.) |
|---|
| A11 | 05 | 1 | | @1 MARTIN (J. I.) |
|---|
| A11 | 06 | 1 | | @1 PEREZ (J. M.) |
|---|
| A12 | 01 | 1 | | @1 AMIN (Adnan) @9 ed. |
|---|
| A12 | 02 | 1 | | @1 DORI (Dov) @9 ed. |
|---|
| A12 | 03 | 1 | | @1 PUDIL (Pavel) @9 ed. |
|---|
| A12 | 04 | 1 | | @1 FREEMAN (Herbert) @9 ed. |
|---|
| A14 | 01 | | | @1 Computer Architecture and Technology Department, The Basque Country University (UPV/EHU), Aptdo. 649 @2 20080, Donostia @3 ESP @Z 1 aut. @Z 2 aut. @Z 3 aut. @Z 4 aut. @Z 5 aut. @Z 6 aut. |
|---|
| A20 | | | | @1 975-980 |
|---|
| A21 | | | | @1 1998 |
|---|
| A23 | 01 | | | @0 ENG |
|---|
| A26 | 01 | | | @0 3-540-64858-5 |
|---|
| A43 | 01 | | | @1 INIST @2 16343 @5 354000076409571050 |
|---|
| A44 | | | | @0 0000 @1 © 1998 INIST-CNRS. All rights reserved. |
|---|
| A45 | | | | @0 6 ref. |
|---|
| A47 | 01 | 1 | | @0 98-0504545 |
|---|
| A60 | | | | @1 P @2 C |
|---|
| A61 | | | | @0 A |
|---|
| A64 | | 1 | | @0 Lecture notes in computer science |
|---|
| A66 | 01 | | | @0 DEU |
|---|
| A66 | 02 | | | @0 USA |
|---|
| C01 | 01 | | ENG | @0 This work presents a solution to the problem of the segmentation of digits in forms characterized by its low quality, as well as the existence of breaks and touching digits. We propose a new function of segmentation that adds to two traditional techniques (vertical projections and Tsujimoto metric) information of background of the digit. Unlike other techniques reported in the literature, ours obtains a near-optimum number of break points in fields containing broken, blurred and touching characters, leading to high accuracy in the global OCR system. The accuracy obtained in the segmentation of the forms fields is of 99,74% on a sample of 11,283 fields of 144 forms of low quality, which provides a final accuracy to the automatic recognition process of 99.42% of digits correctly classified. |
|---|
| C02 | 01 | X | | @0 001D02C03 |
|---|
| C03 | 01 | X | FRE | @0 Analyse image @5 01 |
|---|
| C03 | 01 | X | ENG | @0 Image analysis @5 01 |
|---|
| C03 | 01 | X | SPA | @0 Análisis imagen @5 01 |
|---|
| C03 | 02 | 1 | FRE | @0 Segmentation image @5 02 |
|---|
| C03 | 02 | 1 | ENG | @0 Image segmentation @5 02 |
|---|
| C03 | 03 | X | FRE | @0 Analyse forme @5 03 |
|---|
| C03 | 03 | X | ENG | @0 Pattern analysis @5 03 |
|---|
| C03 | 03 | X | SPA | @0 Análisis forma @5 03 |
|---|
| C03 | 04 | X | FRE | @0 Reconnaissance forme @5 04 |
|---|
| C03 | 04 | X | ENG | @0 Pattern recognition @5 04 |
|---|
| C03 | 04 | X | GER | @0 Mustererkennung @5 04 |
|---|
| C03 | 04 | X | SPA | @0 Reconocimiento patrón @5 04 |
|---|
| C03 | 05 | X | FRE | @0 Reconnaissance optique caractère @5 05 |
|---|
| C03 | 05 | X | ENG | @0 Optical character recognition @5 05 |
|---|
| C03 | 05 | X | SPA | @0 Reconocimento óptico de caracteres @5 05 |
|---|
| C03 | 06 | 3 | FRE | @0 Reconnaissance écriture @5 06 |
|---|
| C03 | 06 | 3 | ENG | @0 Handwriting recognition @5 06 |
|---|
| N21 | | | | @1 327 |
|---|
|
|---|
| pR |
| A30 | 01 | 1 | ENG | @1 Joint IAPR international workshops @3 Sydney AUS @4 1998-08-11 |
|---|
| A30 | 02 | 1 | ENG | @1 SSPR '98 : International workshop on structural and syntactic pattern recognition @2 7 @3 Sydney AUS @4 1998-08-11 |
|---|
| A30 | 03 | 1 | ENG | @1 SPR '98 : International workshop on stasticial techniques in pattern recognition @2 2 @3 Sydney AUS @4 1998-08-11 |
|---|
|
|---|
Format Inist (serveur)
| NO : | PASCAL 98-0504545 INIST |
|---|
| ET : | A new cost function for typewritten digits segmentation |
|---|
| AU : | RODRIGUEZ (C.); MUGUERZA (J.); NAVARRO (M.); ZARATE (A.); MARTIN (J. I.); PEREZ (J. M.); AMIN (Adnan); DORI (Dov); PUDIL (Pavel); FREEMAN (Herbert) |
|---|
| AF : | Computer Architecture and Technology Department, The Basque Country University (UPV/EHU), Aptdo. 649/20080, Donostia/Espagne (1 aut., 2 aut., 3 aut., 4 aut., 5 aut., 6 aut.) |
|---|
| DT : | Publication en série; Congrès; Niveau analytique |
|---|
| SO : | Lecture notes in computer science; ISSN 0302-9743; Allemagne; Da. 1998; Vol. 1451; Pp. 975-980; Bibl. 6 ref. |
|---|
| LA : | Anglais |
|---|
| EA : | This work presents a solution to the problem of the segmentation of digits in forms characterized by its low quality, as well as the existence of breaks and touching digits. We propose a new function of segmentation that adds to two traditional techniques (vertical projections and Tsujimoto metric) information of background of the digit. Unlike other techniques reported in the literature, ours obtains a near-optimum number of break points in fields containing broken, blurred and touching characters, leading to high accuracy in the global OCR system. The accuracy obtained in the segmentation of the forms fields is of 99,74% on a sample of 11,283 fields of 144 forms of low quality, which provides a final accuracy to the automatic recognition process of 99.42% of digits correctly classified. |
|---|
| CC : | 001D02C03 |
|---|
| FD : | Analyse image; Segmentation image; Analyse forme; Reconnaissance forme; Reconnaissance optique caractère; Reconnaissance écriture |
|---|
| ED : | Image analysis; Image segmentation; Pattern analysis; Pattern recognition; Optical character recognition; Handwriting recognition |
|---|
| GD : | Mustererkennung |
|---|
| SD : | Análisis imagen; Análisis forma; Reconocimiento patrón; Reconocimento óptico de caracteres |
|---|
| LO : | INIST-16343.354000076409571050 |
|---|
| ID : | 98-0504545 |
|---|
Links to Exploration step
Pascal:98-0504545
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">A new cost function for typewritten digits segmentation</title>
<author><name sortKey="Rodriguez, C" sort="Rodriguez, C" uniqKey="Rodriguez C" first="C." last="Rodriguez">C. Rodriguez</name>
<affiliation><inist:fA14 i1="01"><s1>Computer Architecture and Technology Department, The Basque Country University (UPV/EHU), Aptdo. 649</s1>
<s2>20080, Donostia</s2>
<s3>ESP</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
<sZ>6 aut.</sZ>
</inist:fA14><author><name sortKey="Muguerza, J" sort="Muguerza, J" uniqKey="Muguerza J" first="J." last="Muguerza">J. Muguerza</name>
<affiliation><inist:fA14 i1="01"><s1>Computer Architecture and Technology Department, The Basque Country University (UPV/EHU), Aptdo. 649</s1>
<s2>20080, Donostia</s2>
<s3>ESP</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
<sZ>6 aut.</sZ>
</inist:fA14><author><name sortKey="Navarro, M" sort="Navarro, M" uniqKey="Navarro M" first="M." last="Navarro">M. Navarro</name>
<affiliation><inist:fA14 i1="01"><s1>Computer Architecture and Technology Department, The Basque Country University (UPV/EHU), Aptdo. 649</s1>
<s2>20080, Donostia</s2>
<s3>ESP</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
<sZ>6 aut.</sZ>
</inist:fA14><author><name sortKey="Zarate, A" sort="Zarate, A" uniqKey="Zarate A" first="A." last="Zarate">A. Zarate</name>
<affiliation><inist:fA14 i1="01"><s1>Computer Architecture and Technology Department, The Basque Country University (UPV/EHU), Aptdo. 649</s1>
<s2>20080, Donostia</s2>
<s3>ESP</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
<sZ>6 aut.</sZ>
</inist:fA14><author><name sortKey="Martin, J I" sort="Martin, J I" uniqKey="Martin J" first="J. I." last="Martin">J. I. Martin</name>
<affiliation><inist:fA14 i1="01"><s1>Computer Architecture and Technology Department, The Basque Country University (UPV/EHU), Aptdo. 649</s1>
<s2>20080, Donostia</s2>
<s3>ESP</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
<sZ>6 aut.</sZ>
</inist:fA14><author><name sortKey="Perez, J M" sort="Perez, J M" uniqKey="Perez J" first="J. M." last="Perez">J. M. Perez</name>
<affiliation><inist:fA14 i1="01"><s1>Computer Architecture and Technology Department, The Basque Country University (UPV/EHU), Aptdo. 649</s1>
<s2>20080, Donostia</s2>
<s3>ESP</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
<sZ>6 aut.</sZ>
</inist:fA14><publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">98-0504545</idno>
<date when="1998">1998</date>
<idno type="stanalyst">PASCAL 98-0504545 INIST</idno>
<idno type="RBID">Pascal:98-0504545</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000854</idno>
</publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">A new cost function for typewritten digits segmentation</title>
<author><name sortKey="Rodriguez, C" sort="Rodriguez, C" uniqKey="Rodriguez C" first="C." last="Rodriguez">C. Rodriguez</name>
<affiliation><inist:fA14 i1="01"><s1>Computer Architecture and Technology Department, The Basque Country University (UPV/EHU), Aptdo. 649</s1>
<s2>20080, Donostia</s2>
<s3>ESP</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
<sZ>6 aut.</sZ>
</inist:fA14><author><name sortKey="Muguerza, J" sort="Muguerza, J" uniqKey="Muguerza J" first="J." last="Muguerza">J. Muguerza</name>
<affiliation><inist:fA14 i1="01"><s1>Computer Architecture and Technology Department, The Basque Country University (UPV/EHU), Aptdo. 649</s1>
<s2>20080, Donostia</s2>
<s3>ESP</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
<sZ>6 aut.</sZ>
</inist:fA14><author><name sortKey="Navarro, M" sort="Navarro, M" uniqKey="Navarro M" first="M." last="Navarro">M. Navarro</name>
<affiliation><inist:fA14 i1="01"><s1>Computer Architecture and Technology Department, The Basque Country University (UPV/EHU), Aptdo. 649</s1>
<s2>20080, Donostia</s2>
<s3>ESP</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
<sZ>6 aut.</sZ>
</inist:fA14><author><name sortKey="Zarate, A" sort="Zarate, A" uniqKey="Zarate A" first="A." last="Zarate">A. Zarate</name>
<affiliation><inist:fA14 i1="01"><s1>Computer Architecture and Technology Department, The Basque Country University (UPV/EHU), Aptdo. 649</s1>
<s2>20080, Donostia</s2>
<s3>ESP</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
<sZ>6 aut.</sZ>
</inist:fA14><author><name sortKey="Martin, J I" sort="Martin, J I" uniqKey="Martin J" first="J. I." last="Martin">J. I. Martin</name>
<affiliation><inist:fA14 i1="01"><s1>Computer Architecture and Technology Department, The Basque Country University (UPV/EHU), Aptdo. 649</s1>
<s2>20080, Donostia</s2>
<s3>ESP</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
<sZ>6 aut.</sZ>
</inist:fA14><author><name sortKey="Perez, J M" sort="Perez, J M" uniqKey="Perez J" first="J. M." last="Perez">J. M. Perez</name>
<affiliation><inist:fA14 i1="01"><s1>Computer Architecture and Technology Department, The Basque Country University (UPV/EHU), Aptdo. 649</s1>
<s2>20080, Donostia</s2>
<s3>ESP</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
<sZ>6 aut.</sZ>
</inist:fA14><series><title level="j" type="main">Lecture notes in computer science</title>
<idno type="ISSN">0302-9743</idno>
<imprint><date when="1998">1998</date>
</imprint><seriesStmt><title level="j" type="main">Lecture notes in computer science</title>
<idno type="ISSN">0302-9743</idno>
</seriesStmt><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Handwriting recognition</term>
<term>Image analysis</term>
<term>Image segmentation</term>
<term>Optical character recognition</term>
<term>Pattern analysis</term>
<term>Pattern recognition</term>
</keywords><keywords scheme="Pascal" xml:lang="fr"><term>Analyse image</term>
<term>Segmentation image</term>
<term>Analyse forme</term>
<term>Reconnaissance forme</term>
<term>Reconnaissance optique caractère</term>
<term>Reconnaissance écriture</term>
</keywords><front><div type="abstract" xml:lang="en">This work presents a solution to the problem of the segmentation of digits in forms characterized by its low quality, as well as the existence of breaks and touching digits. We propose a new function of segmentation that adds to two traditional techniques (vertical projections and Tsujimoto metric) information of background of the digit. Unlike other techniques reported in the literature, ours obtains a near-optimum number of break points in fields containing broken, blurred and touching characters, leading to high accuracy in the global OCR system. The accuracy obtained in the segmentation of the forms fields is of 99,74% on a sample of 11,283 fields of 144 forms of low quality, which provides a final accuracy to the automatic recognition process of 99.42% of digits correctly classified.</div>
</front><inist><standard h6="B"><pA><fA01 i1="01" i2="1"><s0>0302-9743</s0>
</fA01><fA05><s2>1451</s2>
</fA05><fA08 i1="01" i2="1" l="ENG"><s1>A new cost function for typewritten digits segmentation</s1>
</fA08><fA09 i1="01" i2="1" l="ENG"><s1>Advances in pattern recognition : Sydney, 11-13 August 1998</s1>
</fA09><fA11 i1="01" i2="1"><s1>RODRIGUEZ (C.)</s1>
</fA11><fA11 i1="02" i2="1"><s1>MUGUERZA (J.)</s1>
</fA11><fA11 i1="03" i2="1"><s1>NAVARRO (M.)</s1>
</fA11><fA11 i1="04" i2="1"><s1>ZARATE (A.)</s1>
</fA11><fA11 i1="05" i2="1"><s1>MARTIN (J. I.)</s1>
</fA11><fA11 i1="06" i2="1"><s1>PEREZ (J. M.)</s1>
</fA11><fA12 i1="01" i2="1"><s1>AMIN (Adnan)</s1>
<s9>ed.</s9>
</fA12><fA12 i1="02" i2="1"><s1>DORI (Dov)</s1>
<s9>ed.</s9>
</fA12><fA12 i1="03" i2="1"><s1>PUDIL (Pavel)</s1>
<s9>ed.</s9>
</fA12><fA12 i1="04" i2="1"><s1>FREEMAN (Herbert)</s1>
<s9>ed.</s9>
</fA12><fA14 i1="01"><s1>Computer Architecture and Technology Department, The Basque Country University (UPV/EHU), Aptdo. 649</s1>
<s2>20080, Donostia</s2>
<s3>ESP</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
<sZ>6 aut.</sZ>
</fA14><fA20><s1>975-980</s1>
</fA20><fA21><s1>1998</s1>
</fA21><fA23 i1="01"><s0>ENG</s0>
</fA23><fA26 i1="01"><s0>3-540-64858-5</s0>
</fA26><fA43 i1="01"><s1>INIST</s1>
<s2>16343</s2>
<s5>354000076409571050</s5>
</fA43><fA44><s0>0000</s0>
<s1>© 1998 INIST-CNRS. All rights reserved.</s1>
</fA44><fA45><s0>6 ref.</s0>
</fA45><fA47 i1="01" i2="1"><s0>98-0504545</s0>
</fA47><fA60><s1>P</s1>
<s2>C</s2>
</fA60><fA64 i2="1"><s0>Lecture notes in computer science</s0>
</fA64><fA66 i1="01"><s0>DEU</s0>
</fA66><fA66 i1="02"><s0>USA</s0>
</fA66><fC01 i1="01" l="ENG"><s0>This work presents a solution to the problem of the segmentation of digits in forms characterized by its low quality, as well as the existence of breaks and touching digits. We propose a new function of segmentation that adds to two traditional techniques (vertical projections and Tsujimoto metric) information of background of the digit. Unlike other techniques reported in the literature, ours obtains a near-optimum number of break points in fields containing broken, blurred and touching characters, leading to high accuracy in the global OCR system. The accuracy obtained in the segmentation of the forms fields is of 99,74% on a sample of 11,283 fields of 144 forms of low quality, which provides a final accuracy to the automatic recognition process of 99.42% of digits correctly classified.</s0>
</fC01><fC02 i1="01" i2="X"><s0>001D02C03</s0>
</fC02><fC03 i1="01" i2="X" l="FRE"><s0>Analyse image</s0>
<s5>01</s5>
</fC03><fC03 i1="01" i2="X" l="ENG"><s0>Image analysis</s0>
<s5>01</s5>
</fC03><fC03 i1="01" i2="X" l="SPA"><s0>Análisis imagen</s0>
<s5>01</s5>
</fC03><fC03 i1="02" i2="1" l="FRE"><s0>Segmentation image</s0>
<s5>02</s5>
</fC03><fC03 i1="02" i2="1" l="ENG"><s0>Image segmentation</s0>
<s5>02</s5>
</fC03><fC03 i1="03" i2="X" l="FRE"><s0>Analyse forme</s0>
<s5>03</s5>
</fC03><fC03 i1="03" i2="X" l="ENG"><s0>Pattern analysis</s0>
<s5>03</s5>
</fC03><fC03 i1="03" i2="X" l="SPA"><s0>Análisis forma</s0>
<s5>03</s5>
</fC03><fC03 i1="04" i2="X" l="FRE"><s0>Reconnaissance forme</s0>
<s5>04</s5>
</fC03><fC03 i1="04" i2="X" l="ENG"><s0>Pattern recognition</s0>
<s5>04</s5>
</fC03><fC03 i1="04" i2="X" l="GER"><s0>Mustererkennung</s0>
<s5>04</s5>
</fC03><fC03 i1="04" i2="X" l="SPA"><s0>Reconocimiento patrón</s0>
<s5>04</s5>
</fC03><fC03 i1="05" i2="X" l="FRE"><s0>Reconnaissance optique caractère</s0>
<s5>05</s5>
</fC03><fC03 i1="05" i2="X" l="ENG"><s0>Optical character recognition</s0>
<s5>05</s5>
</fC03><fC03 i1="05" i2="X" l="SPA"><s0>Reconocimento óptico de caracteres</s0>
<s5>05</s5>
</fC03><fC03 i1="06" i2="3" l="FRE"><s0>Reconnaissance écriture</s0>
<s5>06</s5>
</fC03><fC03 i1="06" i2="3" l="ENG"><s0>Handwriting recognition</s0>
<s5>06</s5>
</fC03><fN21><s1>327</s1>
</fN21><pR><fA30 i1="01" i2="1" l="ENG"><s1>Joint IAPR international workshops</s1>
<s3>Sydney AUS</s3>
<s4>1998-08-11</s4>
</fA30><fA30 i1="02" i2="1" l="ENG"><s1>SSPR '98 : International workshop on structural and syntactic pattern recognition</s1>
<s2>7</s2>
<s3>Sydney AUS</s3>
<s4>1998-08-11</s4>
</fA30><fA30 i1="03" i2="1" l="ENG"><s1>SPR '98 : International workshop on stasticial techniques in pattern recognition</s1>
<s2>2</s2>
<s3>Sydney AUS</s3>
<s4>1998-08-11</s4>
</fA30><server><NO>PASCAL 98-0504545 INIST</NO>
<ET>A new cost function for typewritten digits segmentation</ET>
<AU>RODRIGUEZ (C.); MUGUERZA (J.); NAVARRO (M.); ZARATE (A.); MARTIN (J. I.); PEREZ (J. M.); AMIN (Adnan); DORI (Dov); PUDIL (Pavel); FREEMAN (Herbert)</AU>
<AF>Computer Architecture and Technology Department, The Basque Country University (UPV/EHU), Aptdo. 649/20080, Donostia/Espagne (1 aut., 2 aut., 3 aut., 4 aut., 5 aut., 6 aut.)</AF>
<DT>Publication en série; Congrès; Niveau analytique</DT>
<SO>Lecture notes in computer science; ISSN 0302-9743; Allemagne; Da. 1998; Vol. 1451; Pp. 975-980; Bibl. 6 ref.</SO>
<LA>Anglais</LA>
<EA>This work presents a solution to the problem of the segmentation of digits in forms characterized by its low quality, as well as the existence of breaks and touching digits. We propose a new function of segmentation that adds to two traditional techniques (vertical projections and Tsujimoto metric) information of background of the digit. Unlike other techniques reported in the literature, ours obtains a near-optimum number of break points in fields containing broken, blurred and touching characters, leading to high accuracy in the global OCR system. The accuracy obtained in the segmentation of the forms fields is of 99,74% on a sample of 11,283 fields of 144 forms of low quality, which provides a final accuracy to the automatic recognition process of 99.42% of digits correctly classified.</EA>
<CC>001D02C03</CC>
<FD>Analyse image; Segmentation image; Analyse forme; Reconnaissance forme; Reconnaissance optique caractère; Reconnaissance écriture</FD>
<ED>Image analysis; Image segmentation; Pattern analysis; Pattern recognition; Optical character recognition; Handwriting recognition</ED>
<GD>Mustererkennung</GD>
<SD>Análisis imagen; Análisis forma; Reconocimiento patrón; Reconocimento óptico de caracteres</SD>
<LO>INIST-16343.354000076409571050</LO>
<ID>98-0504545</ID>
</server>
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 000854 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/PascalFrancis/Corpus/biblio.hfd -nk 000854 | 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:98-0504545
|texte= A new cost function for typewritten digits 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 |  |
