Script identification from Indian documents
Identifieur interne : 000302 ( PascalFrancis/Corpus ); précédent : 000301; suivant : 000303Script identification from Indian documents
Auteurs : GOPAL DATT JOSHI ; Saurabh Garg ; Jayanthi SivaswamySource :
- Lecture notes in computer science [ 0302-9743 ] ; 2006.
Descripteurs français
- Pascal (Inist)
- Reconnaissance forme, Analyse documentaire, Structure document, Reconnaissance caractère, Reconnaissance optique caractère, Texte, Traitement document, Segmentation image, Traitement image, Traitement donnée, Base donnée très grande, Multilinguisme, Archive, Plan classement, Classification hiérarchique, Filtre multicanal, Extraction forme, Filtre Gabor, Optimisation, Conception optimale, Méthode échelle multiple.
English descriptors
- KwdEn :
- Archive, Character recognition, Classification scheme, Data processing, Document analysis, Document processing, Document structure, Gabor filter, Hierarchical classification, Image processing, Image segmentation, Multichannel filter, Multilingualism, Multiscale method, Optical character recognition, Optimal design, Optimization, Pattern extraction, Pattern recognition, Text, Very large databases.
Abstract
Automatic identification of a script in a given document image facilitates many important applications such as automatic archiving of multilingual documents, searching online archives of document images and for the selection of script specific OCR in a multilingual environment. In this paper, we present a scheme to identify different Indian scripts from a document image. This scheme employs hierarchical classification which uses features consistent with human perception. Such features are extracted from the responses of a multi-channel log-Gabor filter bank, designed at an optimal scale and multiple orientations. In the first stage, the classifier groups the scripts into five major classes using global features. At the next stage, a sub-classification is performed based on script-specific features. All features are extracted globally from a given text block which does not require any complex and reliable segmentation of the document image into lines and characters. Thus the proposed scheme is efficient and can be used for many practical applications which require processing large volumes of data. The scheme has been tested on 10 Indian scripts and found to be robust to skew generated in the process of scanning and relatively insensitive to change in font size. This proposed system achieves an overall classification accuracy of 97.11% on a large testing data set. These results serve to establish the utility of global approach to classification of scripts.
Notice en format standard (ISO 2709)
Pour connaître la documentation sur le format Inist Standard.
pA |
|
||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
pR |
|
Format Inist (serveur)
NO : | PASCAL 08-0029049 INIST |
---|---|
ET : | Script identification from Indian documents |
AU : | GOPAL DATT JOSHI; GARG (Saurabh); SIVASWAMY (Jayanthi); BUNKE (Horst); SPITZ (A. Lawrence) |
AF : | Centre for Visual Information Technology, IIIT Hyderabad/Inde (1 aut., 2 aut., 3 aut.) |
DT : | Publication en série; Congrès; Niveau analytique |
SO : | Lecture notes in computer science; ISSN 0302-9743; Allemagne; Da. 2006; Vol. 3872; Pp. 255-267; Bibl. 15 ref. |
LA : | Anglais |
EA : | Automatic identification of a script in a given document image facilitates many important applications such as automatic archiving of multilingual documents, searching online archives of document images and for the selection of script specific OCR in a multilingual environment. In this paper, we present a scheme to identify different Indian scripts from a document image. This scheme employs hierarchical classification which uses features consistent with human perception. Such features are extracted from the responses of a multi-channel log-Gabor filter bank, designed at an optimal scale and multiple orientations. In the first stage, the classifier groups the scripts into five major classes using global features. At the next stage, a sub-classification is performed based on script-specific features. All features are extracted globally from a given text block which does not require any complex and reliable segmentation of the document image into lines and characters. Thus the proposed scheme is efficient and can be used for many practical applications which require processing large volumes of data. The scheme has been tested on 10 Indian scripts and found to be robust to skew generated in the process of scanning and relatively insensitive to change in font size. This proposed system achieves an overall classification accuracy of 97.11% on a large testing data set. These results serve to establish the utility of global approach to classification of scripts. |
CC : | 001D02C03 |
FD : | Reconnaissance forme; Analyse documentaire; Structure document; Reconnaissance caractère; Reconnaissance optique caractère; Texte; Traitement document; Segmentation image; Traitement image; Traitement donnée; Base donnée très grande; Multilinguisme; Archive; Plan classement; Classification hiérarchique; Filtre multicanal; Extraction forme; Filtre Gabor; Optimisation; Conception optimale; Méthode échelle multiple |
ED : | Pattern recognition; Document analysis; Document structure; Character recognition; Optical character recognition; Text; Document processing; Image segmentation; Image processing; Data processing; Very large databases; Multilingualism; Archive; Classification scheme; Hierarchical classification; Multichannel filter; Pattern extraction; Gabor filter; Optimization; Optimal design; Multiscale method |
SD : | Reconocimiento patrón; Análisis documental; Estructura documental; Reconocimiento carácter; Reconocimento óptico de caracteres; Texto; Tratamiento documento; Procesamiento imagen; Tratamiento datos; Multilingüismo; Archivo; Plan clasificación; Clasificación jerarquizada; Filtro multicanal; Extracción forma; Filtro Gabor; Optimización; Concepción optimal; Método escala múltiple |
LO : | INIST-16343.354000153630480230 |
ID : | 08-0029049 |
Links to Exploration step
Pascal:08-0029049Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Script identification from Indian documents</title>
<author><name sortKey="Gopal Datt Joshi" sort="Gopal Datt Joshi" uniqKey="Gopal Datt Joshi" last="Gopal Datt Joshi">GOPAL DATT JOSHI</name>
<affiliation><inist:fA14 i1="01"><s1>Centre for Visual Information Technology, IIIT Hyderabad</s1>
<s3>IND</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Garg, Saurabh" sort="Garg, Saurabh" uniqKey="Garg S" first="Saurabh" last="Garg">Saurabh Garg</name>
<affiliation><inist:fA14 i1="01"><s1>Centre for Visual Information Technology, IIIT Hyderabad</s1>
<s3>IND</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Sivaswamy, Jayanthi" sort="Sivaswamy, Jayanthi" uniqKey="Sivaswamy J" first="Jayanthi" last="Sivaswamy">Jayanthi Sivaswamy</name>
<affiliation><inist:fA14 i1="01"><s1>Centre for Visual Information Technology, IIIT Hyderabad</s1>
<s3>IND</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">08-0029049</idno>
<date when="2006">2006</date>
<idno type="stanalyst">PASCAL 08-0029049 INIST</idno>
<idno type="RBID">Pascal:08-0029049</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000302</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Script identification from Indian documents</title>
<author><name sortKey="Gopal Datt Joshi" sort="Gopal Datt Joshi" uniqKey="Gopal Datt Joshi" last="Gopal Datt Joshi">GOPAL DATT JOSHI</name>
<affiliation><inist:fA14 i1="01"><s1>Centre for Visual Information Technology, IIIT Hyderabad</s1>
<s3>IND</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Garg, Saurabh" sort="Garg, Saurabh" uniqKey="Garg S" first="Saurabh" last="Garg">Saurabh Garg</name>
<affiliation><inist:fA14 i1="01"><s1>Centre for Visual Information Technology, IIIT Hyderabad</s1>
<s3>IND</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Sivaswamy, Jayanthi" sort="Sivaswamy, Jayanthi" uniqKey="Sivaswamy J" first="Jayanthi" last="Sivaswamy">Jayanthi Sivaswamy</name>
<affiliation><inist:fA14 i1="01"><s1>Centre for Visual Information Technology, IIIT Hyderabad</s1>
<s3>IND</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
</analytic>
<series><title level="j" type="main">Lecture notes in computer science</title>
<idno type="ISSN">0302-9743</idno>
<imprint><date when="2006">2006</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><title level="j" type="main">Lecture notes in computer science</title>
<idno type="ISSN">0302-9743</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Archive</term>
<term>Character recognition</term>
<term>Classification scheme</term>
<term>Data processing</term>
<term>Document analysis</term>
<term>Document processing</term>
<term>Document structure</term>
<term>Gabor filter</term>
<term>Hierarchical classification</term>
<term>Image processing</term>
<term>Image segmentation</term>
<term>Multichannel filter</term>
<term>Multilingualism</term>
<term>Multiscale method</term>
<term>Optical character recognition</term>
<term>Optimal design</term>
<term>Optimization</term>
<term>Pattern extraction</term>
<term>Pattern recognition</term>
<term>Text</term>
<term>Very large databases</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Reconnaissance forme</term>
<term>Analyse documentaire</term>
<term>Structure document</term>
<term>Reconnaissance caractère</term>
<term>Reconnaissance optique caractère</term>
<term>Texte</term>
<term>Traitement document</term>
<term>Segmentation image</term>
<term>Traitement image</term>
<term>Traitement donnée</term>
<term>Base donnée très grande</term>
<term>Multilinguisme</term>
<term>Archive</term>
<term>Plan classement</term>
<term>Classification hiérarchique</term>
<term>Filtre multicanal</term>
<term>Extraction forme</term>
<term>Filtre Gabor</term>
<term>Optimisation</term>
<term>Conception optimale</term>
<term>Méthode échelle multiple</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">Automatic identification of a script in a given document image facilitates many important applications such as automatic archiving of multilingual documents, searching online archives of document images and for the selection of script specific OCR in a multilingual environment. In this paper, we present a scheme to identify different Indian scripts from a document image. This scheme employs hierarchical classification which uses features consistent with human perception. Such features are extracted from the responses of a multi-channel log-Gabor filter bank, designed at an optimal scale and multiple orientations. In the first stage, the classifier groups the scripts into five major classes using global features. At the next stage, a sub-classification is performed based on script-specific features. All features are extracted globally from a given text block which does not require any complex and reliable segmentation of the document image into lines and characters. Thus the proposed scheme is efficient and can be used for many practical applications which require processing large volumes of data. The scheme has been tested on 10 Indian scripts and found to be robust to skew generated in the process of scanning and relatively insensitive to change in font size. This proposed system achieves an overall classification accuracy of 97.11% on a large testing data set. These results serve to establish the utility of global approach to classification of scripts.</div>
</front>
</TEI>
<inist><standard h6="B"><pA><fA01 i1="01" i2="1"><s0>0302-9743</s0>
</fA01>
<fA05><s2>3872</s2>
</fA05>
<fA08 i1="01" i2="1" l="ENG"><s1>Script identification from Indian documents</s1>
</fA08>
<fA09 i1="01" i2="1" l="ENG"><s1>Document analysis systems VII : 7th international workshop, DAS 2006, Nelson, New Zealand, February 13-15, 2006 : proceedings</s1>
</fA09>
<fA11 i1="01" i2="1"><s1>GOPAL DATT JOSHI</s1>
</fA11>
<fA11 i1="02" i2="1"><s1>GARG (Saurabh)</s1>
</fA11>
<fA11 i1="03" i2="1"><s1>SIVASWAMY (Jayanthi)</s1>
</fA11>
<fA12 i1="01" i2="1"><s1>BUNKE (Horst)</s1>
<s9>ed.</s9>
</fA12>
<fA12 i1="02" i2="1"><s1>SPITZ (A. Lawrence)</s1>
<s9>ed.</s9>
</fA12>
<fA14 i1="01"><s1>Centre for Visual Information Technology, IIIT Hyderabad</s1>
<s3>IND</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</fA14>
<fA20><s1>255-267</s1>
</fA20>
<fA21><s1>2006</s1>
</fA21>
<fA23 i1="01"><s0>ENG</s0>
</fA23>
<fA26 i1="01"><s0>3-540-32140-3</s0>
</fA26>
<fA43 i1="01"><s1>INIST</s1>
<s2>16343</s2>
<s5>354000153630480230</s5>
</fA43>
<fA44><s0>0000</s0>
<s1>© 2008 INIST-CNRS. All rights reserved.</s1>
</fA44>
<fA45><s0>15 ref.</s0>
</fA45>
<fA47 i1="01" i2="1"><s0>08-0029049</s0>
</fA47>
<fA60><s1>P</s1>
<s2>C</s2>
</fA60>
<fA61><s0>A</s0>
</fA61>
<fA64 i1="01" i2="1"><s0>Lecture notes in computer science</s0>
</fA64>
<fA66 i1="01"><s0>DEU</s0>
</fA66>
<fC01 i1="01" l="ENG"><s0>Automatic identification of a script in a given document image facilitates many important applications such as automatic archiving of multilingual documents, searching online archives of document images and for the selection of script specific OCR in a multilingual environment. In this paper, we present a scheme to identify different Indian scripts from a document image. This scheme employs hierarchical classification which uses features consistent with human perception. Such features are extracted from the responses of a multi-channel log-Gabor filter bank, designed at an optimal scale and multiple orientations. In the first stage, the classifier groups the scripts into five major classes using global features. At the next stage, a sub-classification is performed based on script-specific features. All features are extracted globally from a given text block which does not require any complex and reliable segmentation of the document image into lines and characters. Thus the proposed scheme is efficient and can be used for many practical applications which require processing large volumes of data. The scheme has been tested on 10 Indian scripts and found to be robust to skew generated in the process of scanning and relatively insensitive to change in font size. This proposed system achieves an overall classification accuracy of 97.11% on a large testing data set. These results serve to establish the utility of global approach to classification of scripts.</s0>
</fC01>
<fC02 i1="01" i2="X"><s0>001D02C03</s0>
</fC02>
<fC03 i1="01" i2="X" l="FRE"><s0>Reconnaissance forme</s0>
<s5>01</s5>
</fC03>
<fC03 i1="01" i2="X" l="ENG"><s0>Pattern recognition</s0>
<s5>01</s5>
</fC03>
<fC03 i1="01" i2="X" l="SPA"><s0>Reconocimiento patrón</s0>
<s5>01</s5>
</fC03>
<fC03 i1="02" i2="X" l="FRE"><s0>Analyse documentaire</s0>
<s5>02</s5>
</fC03>
<fC03 i1="02" i2="X" l="ENG"><s0>Document analysis</s0>
<s5>02</s5>
</fC03>
<fC03 i1="02" i2="X" l="SPA"><s0>Análisis documental</s0>
<s5>02</s5>
</fC03>
<fC03 i1="03" i2="X" l="FRE"><s0>Structure document</s0>
<s5>03</s5>
</fC03>
<fC03 i1="03" i2="X" l="ENG"><s0>Document structure</s0>
<s5>03</s5>
</fC03>
<fC03 i1="03" i2="X" l="SPA"><s0>Estructura documental</s0>
<s5>03</s5>
</fC03>
<fC03 i1="04" i2="X" l="FRE"><s0>Reconnaissance caractère</s0>
<s5>06</s5>
</fC03>
<fC03 i1="04" i2="X" l="ENG"><s0>Character recognition</s0>
<s5>06</s5>
</fC03>
<fC03 i1="04" i2="X" l="SPA"><s0>Reconocimiento carácter</s0>
<s5>06</s5>
</fC03>
<fC03 i1="05" i2="X" l="FRE"><s0>Reconnaissance optique caractère</s0>
<s5>07</s5>
</fC03>
<fC03 i1="05" i2="X" l="ENG"><s0>Optical character recognition</s0>
<s5>07</s5>
</fC03>
<fC03 i1="05" i2="X" l="SPA"><s0>Reconocimento óptico de caracteres</s0>
<s5>07</s5>
</fC03>
<fC03 i1="06" i2="X" l="FRE"><s0>Texte</s0>
<s5>08</s5>
</fC03>
<fC03 i1="06" i2="X" l="ENG"><s0>Text</s0>
<s5>08</s5>
</fC03>
<fC03 i1="06" i2="X" l="SPA"><s0>Texto</s0>
<s5>08</s5>
</fC03>
<fC03 i1="07" i2="X" l="FRE"><s0>Traitement document</s0>
<s5>09</s5>
</fC03>
<fC03 i1="07" i2="X" l="ENG"><s0>Document processing</s0>
<s5>09</s5>
</fC03>
<fC03 i1="07" i2="X" l="SPA"><s0>Tratamiento documento</s0>
<s5>09</s5>
</fC03>
<fC03 i1="08" i2="3" l="FRE"><s0>Segmentation image</s0>
<s5>10</s5>
</fC03>
<fC03 i1="08" i2="3" l="ENG"><s0>Image segmentation</s0>
<s5>10</s5>
</fC03>
<fC03 i1="09" i2="X" l="FRE"><s0>Traitement image</s0>
<s5>11</s5>
</fC03>
<fC03 i1="09" i2="X" l="ENG"><s0>Image processing</s0>
<s5>11</s5>
</fC03>
<fC03 i1="09" i2="X" l="SPA"><s0>Procesamiento imagen</s0>
<s5>11</s5>
</fC03>
<fC03 i1="10" i2="X" l="FRE"><s0>Traitement donnée</s0>
<s5>12</s5>
</fC03>
<fC03 i1="10" i2="X" l="ENG"><s0>Data processing</s0>
<s5>12</s5>
</fC03>
<fC03 i1="10" i2="X" l="SPA"><s0>Tratamiento datos</s0>
<s5>12</s5>
</fC03>
<fC03 i1="11" i2="3" l="FRE"><s0>Base donnée très grande</s0>
<s5>13</s5>
</fC03>
<fC03 i1="11" i2="3" l="ENG"><s0>Very large databases</s0>
<s5>13</s5>
</fC03>
<fC03 i1="12" i2="X" l="FRE"><s0>Multilinguisme</s0>
<s5>18</s5>
</fC03>
<fC03 i1="12" i2="X" l="ENG"><s0>Multilingualism</s0>
<s5>18</s5>
</fC03>
<fC03 i1="12" i2="X" l="SPA"><s0>Multilingüismo</s0>
<s5>18</s5>
</fC03>
<fC03 i1="13" i2="X" l="FRE"><s0>Archive</s0>
<s5>19</s5>
</fC03>
<fC03 i1="13" i2="X" l="ENG"><s0>Archive</s0>
<s5>19</s5>
</fC03>
<fC03 i1="13" i2="X" l="SPA"><s0>Archivo</s0>
<s5>19</s5>
</fC03>
<fC03 i1="14" i2="X" l="FRE"><s0>Plan classement</s0>
<s5>20</s5>
</fC03>
<fC03 i1="14" i2="X" l="ENG"><s0>Classification scheme</s0>
<s5>20</s5>
</fC03>
<fC03 i1="14" i2="X" l="SPA"><s0>Plan clasificación</s0>
<s5>20</s5>
</fC03>
<fC03 i1="15" i2="X" l="FRE"><s0>Classification hiérarchique</s0>
<s5>21</s5>
</fC03>
<fC03 i1="15" i2="X" l="ENG"><s0>Hierarchical classification</s0>
<s5>21</s5>
</fC03>
<fC03 i1="15" i2="X" l="SPA"><s0>Clasificación jerarquizada</s0>
<s5>21</s5>
</fC03>
<fC03 i1="16" i2="X" l="FRE"><s0>Filtre multicanal</s0>
<s5>22</s5>
</fC03>
<fC03 i1="16" i2="X" l="ENG"><s0>Multichannel filter</s0>
<s5>22</s5>
</fC03>
<fC03 i1="16" i2="X" l="SPA"><s0>Filtro multicanal</s0>
<s5>22</s5>
</fC03>
<fC03 i1="17" i2="X" l="FRE"><s0>Extraction forme</s0>
<s5>23</s5>
</fC03>
<fC03 i1="17" i2="X" l="ENG"><s0>Pattern extraction</s0>
<s5>23</s5>
</fC03>
<fC03 i1="17" i2="X" l="SPA"><s0>Extracción forma</s0>
<s5>23</s5>
</fC03>
<fC03 i1="18" i2="X" l="FRE"><s0>Filtre Gabor</s0>
<s5>24</s5>
</fC03>
<fC03 i1="18" i2="X" l="ENG"><s0>Gabor filter</s0>
<s5>24</s5>
</fC03>
<fC03 i1="18" i2="X" l="SPA"><s0>Filtro Gabor</s0>
<s5>24</s5>
</fC03>
<fC03 i1="19" i2="X" l="FRE"><s0>Optimisation</s0>
<s5>25</s5>
</fC03>
<fC03 i1="19" i2="X" l="ENG"><s0>Optimization</s0>
<s5>25</s5>
</fC03>
<fC03 i1="19" i2="X" l="SPA"><s0>Optimización</s0>
<s5>25</s5>
</fC03>
<fC03 i1="20" i2="X" l="FRE"><s0>Conception optimale</s0>
<s5>26</s5>
</fC03>
<fC03 i1="20" i2="X" l="ENG"><s0>Optimal design</s0>
<s5>26</s5>
</fC03>
<fC03 i1="20" i2="X" l="SPA"><s0>Concepción optimal</s0>
<s5>26</s5>
</fC03>
<fC03 i1="21" i2="X" l="FRE"><s0>Méthode échelle multiple</s0>
<s5>27</s5>
</fC03>
<fC03 i1="21" i2="X" l="ENG"><s0>Multiscale method</s0>
<s5>27</s5>
</fC03>
<fC03 i1="21" i2="X" l="SPA"><s0>Método escala múltiple</s0>
<s5>27</s5>
</fC03>
<fN21><s1>052</s1>
</fN21>
<fN44 i1="01"><s1>OTO</s1>
</fN44>
<fN82><s1>OTO</s1>
</fN82>
</pA>
<pR><fA30 i1="01" i2="1" l="ENG"><s1>DAS 2006</s1>
<s2>7</s2>
<s3>Nelson NZL</s3>
<s4>2006</s4>
</fA30>
</pR>
</standard>
<server><NO>PASCAL 08-0029049 INIST</NO>
<ET>Script identification from Indian documents</ET>
<AU>GOPAL DATT JOSHI; GARG (Saurabh); SIVASWAMY (Jayanthi); BUNKE (Horst); SPITZ (A. Lawrence)</AU>
<AF>Centre for Visual Information Technology, IIIT Hyderabad/Inde (1 aut., 2 aut., 3 aut.)</AF>
<DT>Publication en série; Congrès; Niveau analytique</DT>
<SO>Lecture notes in computer science; ISSN 0302-9743; Allemagne; Da. 2006; Vol. 3872; Pp. 255-267; Bibl. 15 ref.</SO>
<LA>Anglais</LA>
<EA>Automatic identification of a script in a given document image facilitates many important applications such as automatic archiving of multilingual documents, searching online archives of document images and for the selection of script specific OCR in a multilingual environment. In this paper, we present a scheme to identify different Indian scripts from a document image. This scheme employs hierarchical classification which uses features consistent with human perception. Such features are extracted from the responses of a multi-channel log-Gabor filter bank, designed at an optimal scale and multiple orientations. In the first stage, the classifier groups the scripts into five major classes using global features. At the next stage, a sub-classification is performed based on script-specific features. All features are extracted globally from a given text block which does not require any complex and reliable segmentation of the document image into lines and characters. Thus the proposed scheme is efficient and can be used for many practical applications which require processing large volumes of data. The scheme has been tested on 10 Indian scripts and found to be robust to skew generated in the process of scanning and relatively insensitive to change in font size. This proposed system achieves an overall classification accuracy of 97.11% on a large testing data set. These results serve to establish the utility of global approach to classification of scripts.</EA>
<CC>001D02C03</CC>
<FD>Reconnaissance forme; Analyse documentaire; Structure document; Reconnaissance caractère; Reconnaissance optique caractère; Texte; Traitement document; Segmentation image; Traitement image; Traitement donnée; Base donnée très grande; Multilinguisme; Archive; Plan classement; Classification hiérarchique; Filtre multicanal; Extraction forme; Filtre Gabor; Optimisation; Conception optimale; Méthode échelle multiple</FD>
<ED>Pattern recognition; Document analysis; Document structure; Character recognition; Optical character recognition; Text; Document processing; Image segmentation; Image processing; Data processing; Very large databases; Multilingualism; Archive; Classification scheme; Hierarchical classification; Multichannel filter; Pattern extraction; Gabor filter; Optimization; Optimal design; Multiscale method</ED>
<SD>Reconocimiento patrón; Análisis documental; Estructura documental; Reconocimiento carácter; Reconocimento óptico de caracteres; Texto; Tratamiento documento; Procesamiento imagen; Tratamiento datos; Multilingüismo; Archivo; Plan clasificación; Clasificación jerarquizada; Filtro multicanal; Extracción forma; Filtro Gabor; Optimización; Concepción optimal; Método escala múltiple</SD>
<LO>INIST-16343.354000153630480230</LO>
<ID>08-0029049</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 000302 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/PascalFrancis/Corpus/biblio.hfd -nk 000302 | 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:08-0029049 |texte= Script identification from Indian documents }}
![]() | This area was generated with Dilib version V0.6.32. | ![]() |