Enabling search over large collections of telugu document images : An automatic annotation based approach
Identifieur interne :
000311 ( PascalFrancis/Corpus );
précédent :
000310;
suivant :
000312
Enabling search over large collections of telugu document images : An automatic annotation based approach
Auteurs : K. Pramod Sankar ;
C. V. JawaharSource :
-
Lecture notes in computer science [ 0302-9743 ] ; 2006.
RBID : Pascal:07-0525710
Descripteurs français
- Pascal (Inist)
- Vision ordinateur,
Banque image,
Traitement image,
Texte,
Accès document,
Recherche information,
Recherche image,
Reconnaissance caractère,
Reconnaissance optique caractère,
Classification image,
Classification forme,
Extensibilité,
Reconnaissance forme,
Annotation,
Temps recherche,
Multilinguisme,
Recherche par contenu,
Réponse temporelle,
Moteur recherche,
Grappe calculateur.
English descriptors
- KwdEn :
- Annotation,
Character recognition,
Cluster computing,
Computer vision,
Content-based retrieval,
Document access,
Image classification,
Image databank,
Image processing,
Image retrieval,
Information retrieval,
Multilingualism,
Optical character recognition,
Pattern classification,
Pattern recognition,
Scalability,
Search engine,
Search time,
Text,
Time response.
Abstract
For the first time, search is enabled over a massive collection of 21 Million word images from digitized document images. This work advances the state-of-the-art on multiple fronts: i) Indian language document images are made searchable by textual queries, ii) interactive content-level access is provided to document images for search and retrieval, iii) a novel recognition-free approach, that does not require an OCR, is adapted and validated iv) a suite of image processing and pattern classification algorithms are proposed to efficiently automate the process and v) the scalability of the solution is demonstrated over a large collection of 500 digitised books consisting of 75,000 pages. Character recognition based approaches yield poor results for developing search engines for Indian language document images, due to the complexity of the script and the poor quality of the documents. Recognition free approaches, based on word-spotting, are not directly scalable to large collections, due to the computational complexity of matching images in the feature space. For example, if it requires 1 mSec to match two images, the retrieval of documents to a single query, from a large collection like ours, would require close to a day's time. In this paper we propose a novel automatic annotation based approach to provide textual description of document images. With a one time, offline computational effort, we are able to build a text-based retrieval system, over annotated images. This system has an interactive response time of about 0.01 second. However, we pay the price in the form of massive offline computation, which is performed on a cluster of 35 computers, for about a month. Our procedure is highly automatic, requiring minimal human intervention.
Notice en format standard (ISO 2709)
Pour connaître la documentation sur le format Inist Standard.
| pA |
| A01 | 01 | 1 | | @0 0302-9743 |
|---|
| A05 | | | | @2 4338 |
|---|
| A08 | 01 | 1 | ENG | @1 Enabling search over large collections of telugu document images : An automatic annotation based approach |
|---|
| A09 | 01 | 1 | ENG | @1 Computer vision, graphics and image processing : 5th Indian conference, ICVGIP 2006, Madurai, India, December 13-16, 2006 : proceedings |
|---|
| A11 | 01 | 1 | | @1 PRAMOD SANKAR (K.) |
|---|
| A11 | 02 | 1 | | @1 JAWAHAR (C. V.) |
|---|
| A12 | 01 | 1 | | @1 KALRA (Prem K.) @9 ed. |
|---|
| A12 | 02 | 1 | | @1 PELEG (Shmuel) @9 ed. |
|---|
| A14 | 01 | | | @1 Centre for Visual Information Technology, International Institute of Information Technology @2 Hyderabad @3 IND @Z 1 aut. @Z 2 aut. |
|---|
| A20 | | | | @1 837-848 |
|---|
| A21 | | | | @1 2006 |
|---|
| A23 | 01 | | | @0 ENG |
|---|
| A26 | 01 | | | @0 3-540-68301-1 |
|---|
| A43 | 01 | | | @1 INIST @2 16343 @5 354000153627190750 |
|---|
| A44 | | | | @0 0000 @1 © 2007 INIST-CNRS. All rights reserved. |
|---|
| A45 | | | | @0 23 ref. |
|---|
| A47 | 01 | 1 | | @0 07-0525710 |
|---|
| A60 | | | | @1 P @2 C |
|---|
| A61 | | | | @0 A |
|---|
| A64 | 01 | 1 | | @0 Lecture notes in computer science |
|---|
| A66 | 01 | | | @0 DEU |
|---|
| A66 | 02 | | | @0 USA |
|---|
| C01 | 01 | | ENG | @0 For the first time, search is enabled over a massive collection of 21 Million word images from digitized document images. This work advances the state-of-the-art on multiple fronts: i) Indian language document images are made searchable by textual queries, ii) interactive content-level access is provided to document images for search and retrieval, iii) a novel recognition-free approach, that does not require an OCR, is adapted and validated iv) a suite of image processing and pattern classification algorithms are proposed to efficiently automate the process and v) the scalability of the solution is demonstrated over a large collection of 500 digitised books consisting of 75,000 pages. Character recognition based approaches yield poor results for developing search engines for Indian language document images, due to the complexity of the script and the poor quality of the documents. Recognition free approaches, based on word-spotting, are not directly scalable to large collections, due to the computational complexity of matching images in the feature space. For example, if it requires 1 mSec to match two images, the retrieval of documents to a single query, from a large collection like ours, would require close to a day's time. In this paper we propose a novel automatic annotation based approach to provide textual description of document images. With a one time, offline computational effort, we are able to build a text-based retrieval system, over annotated images. This system has an interactive response time of about 0.01 second. However, we pay the price in the form of massive offline computation, which is performed on a cluster of 35 computers, for about a month. Our procedure is highly automatic, requiring minimal human intervention. |
|---|
| C02 | 01 | X | | @0 001D02C03 |
|---|
| C02 | 02 | X | | @0 001D02B07D |
|---|
| C02 | 03 | X | | @0 001D02B04 |
|---|
| C03 | 01 | X | FRE | @0 Vision ordinateur @5 01 |
|---|
| C03 | 01 | X | ENG | @0 Computer vision @5 01 |
|---|
| C03 | 01 | X | SPA | @0 Visión ordenador @5 01 |
|---|
| C03 | 02 | X | FRE | @0 Banque image @5 06 |
|---|
| C03 | 02 | X | ENG | @0 Image databank @5 06 |
|---|
| C03 | 02 | X | SPA | @0 Banco imagen @5 06 |
|---|
| C03 | 03 | X | FRE | @0 Traitement image @5 07 |
|---|
| C03 | 03 | X | ENG | @0 Image processing @5 07 |
|---|
| C03 | 03 | X | SPA | @0 Procesamiento imagen @5 07 |
|---|
| C03 | 04 | X | FRE | @0 Texte @5 08 |
|---|
| C03 | 04 | X | ENG | @0 Text @5 08 |
|---|
| C03 | 04 | X | SPA | @0 Texto @5 08 |
|---|
| C03 | 05 | X | FRE | @0 Accès document @5 09 |
|---|
| C03 | 05 | X | ENG | @0 Document access @5 09 |
|---|
| C03 | 05 | X | SPA | @0 Acceso documento @5 09 |
|---|
| C03 | 06 | X | FRE | @0 Recherche information @5 10 |
|---|
| C03 | 06 | X | ENG | @0 Information retrieval @5 10 |
|---|
| C03 | 06 | X | SPA | @0 Búsqueda información @5 10 |
|---|
| C03 | 07 | 3 | FRE | @0 Recherche image @5 11 |
|---|
| C03 | 07 | 3 | ENG | @0 Image retrieval @5 11 |
|---|
| C03 | 08 | X | FRE | @0 Reconnaissance caractère @5 12 |
|---|
| C03 | 08 | X | ENG | @0 Character recognition @5 12 |
|---|
| C03 | 08 | X | SPA | @0 Reconocimiento carácter @5 12 |
|---|
| C03 | 09 | X | FRE | @0 Reconnaissance optique caractère @5 13 |
|---|
| C03 | 09 | X | ENG | @0 Optical character recognition @5 13 |
|---|
| C03 | 09 | X | SPA | @0 Reconocimento óptico de caracteres @5 13 |
|---|
| C03 | 10 | 3 | FRE | @0 Classification image @5 14 |
|---|
| C03 | 10 | 3 | ENG | @0 Image classification @5 14 |
|---|
| C03 | 11 | 3 | FRE | @0 Classification forme @5 15 |
|---|
| C03 | 11 | 3 | ENG | @0 Pattern classification @5 15 |
|---|
| C03 | 12 | X | FRE | @0 Extensibilité @5 16 |
|---|
| C03 | 12 | X | ENG | @0 Scalability @5 16 |
|---|
| C03 | 12 | X | SPA | @0 Estensibilidad @5 16 |
|---|
| C03 | 13 | X | FRE | @0 Reconnaissance forme @5 17 |
|---|
| C03 | 13 | X | ENG | @0 Pattern recognition @5 17 |
|---|
| C03 | 13 | X | SPA | @0 Reconocimiento patrón @5 17 |
|---|
| C03 | 14 | X | FRE | @0 Annotation @5 18 |
|---|
| C03 | 14 | X | ENG | @0 Annotation @5 18 |
|---|
| C03 | 14 | X | SPA | @0 Anotación @5 18 |
|---|
| C03 | 15 | X | FRE | @0 Temps recherche @5 19 |
|---|
| C03 | 15 | X | ENG | @0 Search time @5 19 |
|---|
| C03 | 15 | X | SPA | @0 Tiempo búsqueda @5 19 |
|---|
| C03 | 16 | X | FRE | @0 Multilinguisme @5 20 |
|---|
| C03 | 16 | X | ENG | @0 Multilingualism @5 20 |
|---|
| C03 | 16 | X | SPA | @0 Multilingüismo @5 20 |
|---|
| C03 | 17 | 3 | FRE | @0 Recherche par contenu @5 21 |
|---|
| C03 | 17 | 3 | ENG | @0 Content-based retrieval @5 21 |
|---|
| C03 | 18 | X | FRE | @0 Réponse temporelle @5 22 |
|---|
| C03 | 18 | X | ENG | @0 Time response @5 22 |
|---|
| C03 | 18 | X | SPA | @0 Respuesta temporal @5 22 |
|---|
| C03 | 19 | X | FRE | @0 Moteur recherche @5 41 |
|---|
| C03 | 19 | X | ENG | @0 Search engine @5 41 |
|---|
| C03 | 19 | X | SPA | @0 Buscador @5 41 |
|---|
| C03 | 20 | X | FRE | @0 Grappe calculateur @4 CD @5 96 |
|---|
| C03 | 20 | X | ENG | @0 Cluster computing @4 CD @5 96 |
|---|
| C03 | 20 | X | SPA | @0 Racimo calculadura @4 CD @5 96 |
|---|
| N21 | | | | @1 344 |
|---|
| N44 | 01 | | | @1 OTO |
|---|
| N82 | | | | @1 OTO |
|---|
|
|---|
| pR |
| A30 | 01 | 1 | ENG | @1 Indian Conference on Computer Vision Graphics and Image Processing @2 5 @3 Madurai IND @4 2006 |
|---|
|
|---|
Format Inist (serveur)
| NO : | PASCAL 07-0525710 INIST |
|---|
| ET : | Enabling search over large collections of telugu document images : An automatic annotation based approach |
|---|
| AU : | PRAMOD SANKAR (K.); JAWAHAR (C. V.); KALRA (Prem K.); PELEG (Shmuel) |
|---|
| AF : | Centre for Visual Information Technology, International Institute of Information Technology/Hyderabad/Inde (1 aut., 2 aut.) |
|---|
| DT : | Publication en série; Congrès; Niveau analytique |
|---|
| SO : | Lecture notes in computer science; ISSN 0302-9743; Allemagne; Da. 2006; Vol. 4338; Pp. 837-848; Bibl. 23 ref. |
|---|
| LA : | Anglais |
|---|
| EA : | For the first time, search is enabled over a massive collection of 21 Million word images from digitized document images. This work advances the state-of-the-art on multiple fronts: i) Indian language document images are made searchable by textual queries, ii) interactive content-level access is provided to document images for search and retrieval, iii) a novel recognition-free approach, that does not require an OCR, is adapted and validated iv) a suite of image processing and pattern classification algorithms are proposed to efficiently automate the process and v) the scalability of the solution is demonstrated over a large collection of 500 digitised books consisting of 75,000 pages. Character recognition based approaches yield poor results for developing search engines for Indian language document images, due to the complexity of the script and the poor quality of the documents. Recognition free approaches, based on word-spotting, are not directly scalable to large collections, due to the computational complexity of matching images in the feature space. For example, if it requires 1 mSec to match two images, the retrieval of documents to a single query, from a large collection like ours, would require close to a day's time. In this paper we propose a novel automatic annotation based approach to provide textual description of document images. With a one time, offline computational effort, we are able to build a text-based retrieval system, over annotated images. This system has an interactive response time of about 0.01 second. However, we pay the price in the form of massive offline computation, which is performed on a cluster of 35 computers, for about a month. Our procedure is highly automatic, requiring minimal human intervention. |
|---|
| CC : | 001D02C03; 001D02B07D; 001D02B04 |
|---|
| FD : | Vision ordinateur; Banque image; Traitement image; Texte; Accès document; Recherche information; Recherche image; Reconnaissance caractère; Reconnaissance optique caractère; Classification image; Classification forme; Extensibilité; Reconnaissance forme; Annotation; Temps recherche; Multilinguisme; Recherche par contenu; Réponse temporelle; Moteur recherche; Grappe calculateur |
|---|
| ED : | Computer vision; Image databank; Image processing; Text; Document access; Information retrieval; Image retrieval; Character recognition; Optical character recognition; Image classification; Pattern classification; Scalability; Pattern recognition; Annotation; Search time; Multilingualism; Content-based retrieval; Time response; Search engine; Cluster computing |
|---|
| SD : | Visión ordenador; Banco imagen; Procesamiento imagen; Texto; Acceso documento; Búsqueda información; Reconocimiento carácter; Reconocimento óptico de caracteres; Estensibilidad; Reconocimiento patrón; Anotación; Tiempo búsqueda; Multilingüismo; Respuesta temporal; Buscador; Racimo calculadura |
|---|
| LO : | INIST-16343.354000153627190750 |
|---|
| ID : | 07-0525710 |
|---|
Links to Exploration step
Pascal:07-0525710
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Enabling search over large collections of telugu document images : An automatic annotation based approach</title>
<author><name sortKey="Pramod Sankar, K" sort="Pramod Sankar, K" uniqKey="Pramod Sankar K" first="K." last="Pramod Sankar">K. Pramod Sankar</name>
<affiliation><inist:fA14 i1="01"><s1>Centre for Visual Information Technology, International Institute of Information Technology</s1>
<s2>Hyderabad</s2>
<s3>IND</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14><author><name sortKey="Jawahar, C V" sort="Jawahar, C V" uniqKey="Jawahar C" first="C. V." last="Jawahar">C. V. Jawahar</name>
<affiliation><inist:fA14 i1="01"><s1>Centre for Visual Information Technology, International Institute of Information Technology</s1>
<s2>Hyderabad</s2>
<s3>IND</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14><publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">07-0525710</idno>
<date when="2006">2006</date>
<idno type="stanalyst">PASCAL 07-0525710 INIST</idno>
<idno type="RBID">Pascal:07-0525710</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000311</idno>
</publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Enabling search over large collections of telugu document images : An automatic annotation based approach</title>
<author><name sortKey="Pramod Sankar, K" sort="Pramod Sankar, K" uniqKey="Pramod Sankar K" first="K." last="Pramod Sankar">K. Pramod Sankar</name>
<affiliation><inist:fA14 i1="01"><s1>Centre for Visual Information Technology, International Institute of Information Technology</s1>
<s2>Hyderabad</s2>
<s3>IND</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14><author><name sortKey="Jawahar, C V" sort="Jawahar, C V" uniqKey="Jawahar C" first="C. V." last="Jawahar">C. V. Jawahar</name>
<affiliation><inist:fA14 i1="01"><s1>Centre for Visual Information Technology, International Institute of Information Technology</s1>
<s2>Hyderabad</s2>
<s3>IND</s3>
<sZ>1 aut.</sZ>
<sZ>2 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="2006">2006</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>Annotation</term>
<term>Character recognition</term>
<term>Cluster computing</term>
<term>Computer vision</term>
<term>Content-based retrieval</term>
<term>Document access</term>
<term>Image classification</term>
<term>Image databank</term>
<term>Image processing</term>
<term>Image retrieval</term>
<term>Information retrieval</term>
<term>Multilingualism</term>
<term>Optical character recognition</term>
<term>Pattern classification</term>
<term>Pattern recognition</term>
<term>Scalability</term>
<term>Search engine</term>
<term>Search time</term>
<term>Text</term>
<term>Time response</term>
</keywords><keywords scheme="Pascal" xml:lang="fr"><term>Vision ordinateur</term>
<term>Banque image</term>
<term>Traitement image</term>
<term>Texte</term>
<term>Accès document</term>
<term>Recherche information</term>
<term>Recherche image</term>
<term>Reconnaissance caractère</term>
<term>Reconnaissance optique caractère</term>
<term>Classification image</term>
<term>Classification forme</term>
<term>Extensibilité</term>
<term>Reconnaissance forme</term>
<term>Annotation</term>
<term>Temps recherche</term>
<term>Multilinguisme</term>
<term>Recherche par contenu</term>
<term>Réponse temporelle</term>
<term>Moteur recherche</term>
<term>Grappe calculateur</term>
</keywords><front><div type="abstract" xml:lang="en">For the first time, search is enabled over a massive collection of 21 Million word images from digitized document images. This work advances the state-of-the-art on multiple fronts: i) Indian language document images are made searchable by textual queries, ii) interactive content-level access is provided to document images for search and retrieval, iii) a novel recognition-free approach, that does not require an OCR, is adapted and validated iv) a suite of image processing and pattern classification algorithms are proposed to efficiently automate the process and v) the scalability of the solution is demonstrated over a large collection of 500 digitised books consisting of 75,000 pages. Character recognition based approaches yield poor results for developing search engines for Indian language document images, due to the complexity of the script and the poor quality of the documents. Recognition free approaches, based on word-spotting, are not directly scalable to large collections, due to the computational complexity of matching images in the feature space. For example, if it requires 1 mSec to match two images, the retrieval of documents to a single query, from a large collection like ours, would require close to a day's time. In this paper we propose a novel automatic annotation based approach to provide textual description of document images. With a one time, offline computational effort, we are able to build a text-based retrieval system, over annotated images. This system has an interactive response time of about 0.01 second. However, we pay the price in the form of massive offline computation, which is performed on a cluster of 35 computers, for about a month. Our procedure is highly automatic, requiring minimal human intervention.</div>
</front><inist><standard h6="B"><pA><fA01 i1="01" i2="1"><s0>0302-9743</s0>
</fA01><fA05><s2>4338</s2>
</fA05><fA08 i1="01" i2="1" l="ENG"><s1>Enabling search over large collections of telugu document images : An automatic annotation based approach</s1>
</fA08><fA09 i1="01" i2="1" l="ENG"><s1>Computer vision, graphics and image processing : 5th Indian conference, ICVGIP 2006, Madurai, India, December 13-16, 2006 : proceedings</s1>
</fA09><fA11 i1="01" i2="1"><s1>PRAMOD SANKAR (K.)</s1>
</fA11><fA11 i1="02" i2="1"><s1>JAWAHAR (C. V.)</s1>
</fA11><fA12 i1="01" i2="1"><s1>KALRA (Prem K.)</s1>
<s9>ed.</s9>
</fA12><fA12 i1="02" i2="1"><s1>PELEG (Shmuel)</s1>
<s9>ed.</s9>
</fA12><fA14 i1="01"><s1>Centre for Visual Information Technology, International Institute of Information Technology</s1>
<s2>Hyderabad</s2>
<s3>IND</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</fA14><fA20><s1>837-848</s1>
</fA20><fA21><s1>2006</s1>
</fA21><fA23 i1="01"><s0>ENG</s0>
</fA23><fA26 i1="01"><s0>3-540-68301-1</s0>
</fA26><fA43 i1="01"><s1>INIST</s1>
<s2>16343</s2>
<s5>354000153627190750</s5>
</fA43><fA44><s0>0000</s0>
<s1>© 2007 INIST-CNRS. All rights reserved.</s1>
</fA44><fA45><s0>23 ref.</s0>
</fA45><fA47 i1="01" i2="1"><s0>07-0525710</s0>
</fA47><fA60><s1>P</s1>
<s2>C</s2>
</fA60><fA64 i1="01" 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>For the first time, search is enabled over a massive collection of 21 Million word images from digitized document images. This work advances the state-of-the-art on multiple fronts: i) Indian language document images are made searchable by textual queries, ii) interactive content-level access is provided to document images for search and retrieval, iii) a novel recognition-free approach, that does not require an OCR, is adapted and validated iv) a suite of image processing and pattern classification algorithms are proposed to efficiently automate the process and v) the scalability of the solution is demonstrated over a large collection of 500 digitised books consisting of 75,000 pages. Character recognition based approaches yield poor results for developing search engines for Indian language document images, due to the complexity of the script and the poor quality of the documents. Recognition free approaches, based on word-spotting, are not directly scalable to large collections, due to the computational complexity of matching images in the feature space. For example, if it requires 1 mSec to match two images, the retrieval of documents to a single query, from a large collection like ours, would require close to a day's time. In this paper we propose a novel automatic annotation based approach to provide textual description of document images. With a one time, offline computational effort, we are able to build a text-based retrieval system, over annotated images. This system has an interactive response time of about 0.01 second. However, we pay the price in the form of massive offline computation, which is performed on a cluster of 35 computers, for about a month. Our procedure is highly automatic, requiring minimal human intervention.</s0>
</fC01><fC02 i1="01" i2="X"><s0>001D02C03</s0>
</fC02><fC02 i1="02" i2="X"><s0>001D02B07D</s0>
</fC02><fC02 i1="03" i2="X"><s0>001D02B04</s0>
</fC02><fC03 i1="01" i2="X" l="FRE"><s0>Vision ordinateur</s0>
<s5>01</s5>
</fC03><fC03 i1="01" i2="X" l="ENG"><s0>Computer vision</s0>
<s5>01</s5>
</fC03><fC03 i1="01" i2="X" l="SPA"><s0>Visión ordenador</s0>
<s5>01</s5>
</fC03><fC03 i1="02" i2="X" l="FRE"><s0>Banque image</s0>
<s5>06</s5>
</fC03><fC03 i1="02" i2="X" l="ENG"><s0>Image databank</s0>
<s5>06</s5>
</fC03><fC03 i1="02" i2="X" l="SPA"><s0>Banco imagen</s0>
<s5>06</s5>
</fC03><fC03 i1="03" i2="X" l="FRE"><s0>Traitement image</s0>
<s5>07</s5>
</fC03><fC03 i1="03" i2="X" l="ENG"><s0>Image processing</s0>
<s5>07</s5>
</fC03><fC03 i1="03" i2="X" l="SPA"><s0>Procesamiento imagen</s0>
<s5>07</s5>
</fC03><fC03 i1="04" i2="X" l="FRE"><s0>Texte</s0>
<s5>08</s5>
</fC03><fC03 i1="04" i2="X" l="ENG"><s0>Text</s0>
<s5>08</s5>
</fC03><fC03 i1="04" i2="X" l="SPA"><s0>Texto</s0>
<s5>08</s5>
</fC03><fC03 i1="05" i2="X" l="FRE"><s0>Accès document</s0>
<s5>09</s5>
</fC03><fC03 i1="05" i2="X" l="ENG"><s0>Document access</s0>
<s5>09</s5>
</fC03><fC03 i1="05" i2="X" l="SPA"><s0>Acceso documento</s0>
<s5>09</s5>
</fC03><fC03 i1="06" i2="X" l="FRE"><s0>Recherche information</s0>
<s5>10</s5>
</fC03><fC03 i1="06" i2="X" l="ENG"><s0>Information retrieval</s0>
<s5>10</s5>
</fC03><fC03 i1="06" i2="X" l="SPA"><s0>Búsqueda información</s0>
<s5>10</s5>
</fC03><fC03 i1="07" i2="3" l="FRE"><s0>Recherche image</s0>
<s5>11</s5>
</fC03><fC03 i1="07" i2="3" l="ENG"><s0>Image retrieval</s0>
<s5>11</s5>
</fC03><fC03 i1="08" i2="X" l="FRE"><s0>Reconnaissance caractère</s0>
<s5>12</s5>
</fC03><fC03 i1="08" i2="X" l="ENG"><s0>Character recognition</s0>
<s5>12</s5>
</fC03><fC03 i1="08" i2="X" l="SPA"><s0>Reconocimiento carácter</s0>
<s5>12</s5>
</fC03><fC03 i1="09" i2="X" l="FRE"><s0>Reconnaissance optique caractère</s0>
<s5>13</s5>
</fC03><fC03 i1="09" i2="X" l="ENG"><s0>Optical character recognition</s0>
<s5>13</s5>
</fC03><fC03 i1="09" i2="X" l="SPA"><s0>Reconocimento óptico de caracteres</s0>
<s5>13</s5>
</fC03><fC03 i1="10" i2="3" l="FRE"><s0>Classification image</s0>
<s5>14</s5>
</fC03><fC03 i1="10" i2="3" l="ENG"><s0>Image classification</s0>
<s5>14</s5>
</fC03><fC03 i1="11" i2="3" l="FRE"><s0>Classification forme</s0>
<s5>15</s5>
</fC03><fC03 i1="11" i2="3" l="ENG"><s0>Pattern classification</s0>
<s5>15</s5>
</fC03><fC03 i1="12" i2="X" l="FRE"><s0>Extensibilité</s0>
<s5>16</s5>
</fC03><fC03 i1="12" i2="X" l="ENG"><s0>Scalability</s0>
<s5>16</s5>
</fC03><fC03 i1="12" i2="X" l="SPA"><s0>Estensibilidad</s0>
<s5>16</s5>
</fC03><fC03 i1="13" i2="X" l="FRE"><s0>Reconnaissance forme</s0>
<s5>17</s5>
</fC03><fC03 i1="13" i2="X" l="ENG"><s0>Pattern recognition</s0>
<s5>17</s5>
</fC03><fC03 i1="13" i2="X" l="SPA"><s0>Reconocimiento patrón</s0>
<s5>17</s5>
</fC03><fC03 i1="14" i2="X" l="FRE"><s0>Annotation</s0>
<s5>18</s5>
</fC03><fC03 i1="14" i2="X" l="ENG"><s0>Annotation</s0>
<s5>18</s5>
</fC03><fC03 i1="14" i2="X" l="SPA"><s0>Anotación</s0>
<s5>18</s5>
</fC03><fC03 i1="15" i2="X" l="FRE"><s0>Temps recherche</s0>
<s5>19</s5>
</fC03><fC03 i1="15" i2="X" l="ENG"><s0>Search time</s0>
<s5>19</s5>
</fC03><fC03 i1="15" i2="X" l="SPA"><s0>Tiempo búsqueda</s0>
<s5>19</s5>
</fC03><fC03 i1="16" i2="X" l="FRE"><s0>Multilinguisme</s0>
<s5>20</s5>
</fC03><fC03 i1="16" i2="X" l="ENG"><s0>Multilingualism</s0>
<s5>20</s5>
</fC03><fC03 i1="16" i2="X" l="SPA"><s0>Multilingüismo</s0>
<s5>20</s5>
</fC03><fC03 i1="17" i2="3" l="FRE"><s0>Recherche par contenu</s0>
<s5>21</s5>
</fC03><fC03 i1="17" i2="3" l="ENG"><s0>Content-based retrieval</s0>
<s5>21</s5>
</fC03><fC03 i1="18" i2="X" l="FRE"><s0>Réponse temporelle</s0>
<s5>22</s5>
</fC03><fC03 i1="18" i2="X" l="ENG"><s0>Time response</s0>
<s5>22</s5>
</fC03><fC03 i1="18" i2="X" l="SPA"><s0>Respuesta temporal</s0>
<s5>22</s5>
</fC03><fC03 i1="19" i2="X" l="FRE"><s0>Moteur recherche</s0>
<s5>41</s5>
</fC03><fC03 i1="19" i2="X" l="ENG"><s0>Search engine</s0>
<s5>41</s5>
</fC03><fC03 i1="19" i2="X" l="SPA"><s0>Buscador</s0>
<s5>41</s5>
</fC03><fC03 i1="20" i2="X" l="FRE"><s0>Grappe calculateur</s0>
<s4>CD</s4>
<s5>96</s5>
</fC03><fC03 i1="20" i2="X" l="ENG"><s0>Cluster computing</s0>
<s4>CD</s4>
<s5>96</s5>
</fC03><fC03 i1="20" i2="X" l="SPA"><s0>Racimo calculadura</s0>
<s4>CD</s4>
<s5>96</s5>
</fC03><fN21><s1>344</s1>
</fN21><fN44 i1="01"><s1>OTO</s1>
</fN44><fN82><s1>OTO</s1>
</fN82><pR><fA30 i1="01" i2="1" l="ENG"><s1>Indian Conference on Computer Vision Graphics and Image Processing</s1>
<s2>5</s2>
<s3>Madurai IND</s3>
<s4>2006</s4>
</fA30><server><NO>PASCAL 07-0525710 INIST</NO>
<ET>Enabling search over large collections of telugu document images : An automatic annotation based approach</ET>
<AU>PRAMOD SANKAR (K.); JAWAHAR (C. V.); KALRA (Prem K.); PELEG (Shmuel)</AU>
<AF>Centre for Visual Information Technology, International Institute of Information Technology/Hyderabad/Inde (1 aut., 2 aut.)</AF>
<DT>Publication en série; Congrès; Niveau analytique</DT>
<SO>Lecture notes in computer science; ISSN 0302-9743; Allemagne; Da. 2006; Vol. 4338; Pp. 837-848; Bibl. 23 ref.</SO>
<LA>Anglais</LA>
<EA>For the first time, search is enabled over a massive collection of 21 Million word images from digitized document images. This work advances the state-of-the-art on multiple fronts: i) Indian language document images are made searchable by textual queries, ii) interactive content-level access is provided to document images for search and retrieval, iii) a novel recognition-free approach, that does not require an OCR, is adapted and validated iv) a suite of image processing and pattern classification algorithms are proposed to efficiently automate the process and v) the scalability of the solution is demonstrated over a large collection of 500 digitised books consisting of 75,000 pages. Character recognition based approaches yield poor results for developing search engines for Indian language document images, due to the complexity of the script and the poor quality of the documents. Recognition free approaches, based on word-spotting, are not directly scalable to large collections, due to the computational complexity of matching images in the feature space. For example, if it requires 1 mSec to match two images, the retrieval of documents to a single query, from a large collection like ours, would require close to a day's time. In this paper we propose a novel automatic annotation based approach to provide textual description of document images. With a one time, offline computational effort, we are able to build a text-based retrieval system, over annotated images. This system has an interactive response time of about 0.01 second. However, we pay the price in the form of massive offline computation, which is performed on a cluster of 35 computers, for about a month. Our procedure is highly automatic, requiring minimal human intervention.</EA>
<CC>001D02C03; 001D02B07D; 001D02B04</CC>
<FD>Vision ordinateur; Banque image; Traitement image; Texte; Accès document; Recherche information; Recherche image; Reconnaissance caractère; Reconnaissance optique caractère; Classification image; Classification forme; Extensibilité; Reconnaissance forme; Annotation; Temps recherche; Multilinguisme; Recherche par contenu; Réponse temporelle; Moteur recherche; Grappe calculateur</FD>
<ED>Computer vision; Image databank; Image processing; Text; Document access; Information retrieval; Image retrieval; Character recognition; Optical character recognition; Image classification; Pattern classification; Scalability; Pattern recognition; Annotation; Search time; Multilingualism; Content-based retrieval; Time response; Search engine; Cluster computing</ED>
<SD>Visión ordenador; Banco imagen; Procesamiento imagen; Texto; Acceso documento; Búsqueda información; Reconocimiento carácter; Reconocimento óptico de caracteres; Estensibilidad; Reconocimiento patrón; Anotación; Tiempo búsqueda; Multilingüismo; Respuesta temporal; Buscador; Racimo calculadura</SD>
<LO>INIST-16343.354000153627190750</LO>
<ID>07-0525710</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 000311 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/PascalFrancis/Corpus/biblio.hfd -nk 000311 | 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:07-0525710
|texte= Enabling search over large collections of telugu document images : An automatic annotation based approach
}}
| 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 |  |
