Feature extraction by best anisotropic Haar bases in an OCR system
Identifieur interne : 000527 ( PascalFrancis/Corpus ); précédent : 000526; suivant : 000528Feature extraction by best anisotropic Haar bases in an OCR system
Auteurs : Atanas Gotchev ; Dmytro Rusanovskyy ; Roumen Popov ; Karen Egiazarian ; Jaakko AstolaSource :
- SPIE proceedings series [ 1017-2653 ] ; 2004.
Descripteurs français
- Pascal (Inist)
English descriptors
- KwdEn :
Abstract
In this contribution, we explore the best basis paradigm for in feature extraction. According to this paradigm, a library of bases is built and the best basis is found for a given signal class with respect to some cost measure. We aim at constructing a library of anisotropic bases that are suitable for the class of 2-D binarized character images. We consider two, a dyadic and a non-dyadic generalization scheme of the Haar wavelet packets that lead to anisotropic bases. For the non-dyadic case, generalized Fibonacci p-trees are used to derive the space division structure of the transform. Both schemes allow for an efficient O(N log N) best basis search algorithm. The so built extended library of anisotropic Haar bases is used in the problem of optical character recognition. A special case, namely recognition of characters from very low resolution, noisy TV images is investigated. The best Haar basis found is then used in the feature extraction stage of a standard OCR system. We achieve very promising recognition rates for experimental databases of synthetic and real images separated into 59 classes.
Notice en format standard (ISO 2709)
Pour connaître la documentation sur le format Inist Standard.
pA |
|
||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
pR |
|
Format Inist (serveur)
NO : | PASCAL 04-0486698 INIST |
---|---|
ET : | Feature extraction by best anisotropic Haar bases in an OCR system |
AU : | GOTCHEV (Atanas); RUSANOVSKYY (Dmytro); POPOV (Roumen); EGIAZARIAN (Karen); ASTOLA (Jaakko); DOUGHERTY (Edward R.); ASTOLA (Jaakko T.); EGIAZARIAN (Karen O.) |
AF : | Institute of Signal Processing, Tampere University of Technology, P. O. Box 553/33101 Tampere/Finlande (1 aut., 2 aut., 4 aut., 5 aut.); Nokia Research Center, Nokia Group, Summit Avenue/Farnborough, Hampshire/Royaume-Uni (3 aut.) |
DT : | Publication en série; Congrès; Niveau analytique |
SO : | SPIE proceedings series; ISSN 1017-2653; Etats-Unis; Da. 2004; Vol. 5298; Pp. 504-515; Bibl. 9 ref. |
LA : | Anglais |
EA : | In this contribution, we explore the best basis paradigm for in feature extraction. According to this paradigm, a library of bases is built and the best basis is found for a given signal class with respect to some cost measure. We aim at constructing a library of anisotropic bases that are suitable for the class of 2-D binarized character images. We consider two, a dyadic and a non-dyadic generalization scheme of the Haar wavelet packets that lead to anisotropic bases. For the non-dyadic case, generalized Fibonacci p-trees are used to derive the space division structure of the transform. Both schemes allow for an efficient O(N log N) best basis search algorithm. The so built extended library of anisotropic Haar bases is used in the problem of optical character recognition. A special case, namely recognition of characters from very low resolution, noisy TV images is investigated. The best Haar basis found is then used in the feature extraction stage of a standard OCR system. We achieve very promising recognition rates for experimental databases of synthetic and real images separated into 59 classes. |
CC : | 001D04A05A; 001D04A04A2 |
FD : | Extraction caractéristique; Fonction Haar; Reconnaissance optique caractère; Reconnaissance caractère; Algorithme recherche; Basse résolution; Résolution image; Image bruitée; Télévision; Base donnée; Traitement signal; Reconnaissance forme; Qualité image |
ED : | Feature extraction; Haar function; Optical character recognition; Character recognition; Search algorithm; Low resolution; Image resolution; Noisy image; Television; Database; Signal processing; Pattern recognition; Image quality |
SD : | Función Haar; Reconocimento óptico de caracteres; Reconocimiento carácter; Algoritmo búsqueda; Baja resolución; Imagen sonora; Televisión; Base dato; Procesamiento señal; Reconocimiento patrón; Calidad imagen |
LO : | INIST-21760.354000124323740530 |
ID : | 04-0486698 |
Links to Exploration step
Pascal:04-0486698Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Feature extraction by best anisotropic Haar bases in an OCR system</title>
<author><name sortKey="Gotchev, Atanas" sort="Gotchev, Atanas" uniqKey="Gotchev A" first="Atanas" last="Gotchev">Atanas Gotchev</name>
<affiliation><inist:fA14 i1="01"><s1>Institute of Signal Processing, Tampere University of Technology, P. O. Box 553</s1>
<s2>33101 Tampere</s2>
<s3>FIN</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Rusanovskyy, Dmytro" sort="Rusanovskyy, Dmytro" uniqKey="Rusanovskyy D" first="Dmytro" last="Rusanovskyy">Dmytro Rusanovskyy</name>
<affiliation><inist:fA14 i1="01"><s1>Institute of Signal Processing, Tampere University of Technology, P. O. Box 553</s1>
<s2>33101 Tampere</s2>
<s3>FIN</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Popov, Roumen" sort="Popov, Roumen" uniqKey="Popov R" first="Roumen" last="Popov">Roumen Popov</name>
<affiliation><inist:fA14 i1="02"><s1>Nokia Research Center, Nokia Group, Summit Avenue</s1>
<s2>Farnborough, Hampshire</s2>
<s3>GBR</s3>
<sZ>3 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Egiazarian, Karen" sort="Egiazarian, Karen" uniqKey="Egiazarian K" first="Karen" last="Egiazarian">Karen Egiazarian</name>
<affiliation><inist:fA14 i1="01"><s1>Institute of Signal Processing, Tampere University of Technology, P. O. Box 553</s1>
<s2>33101 Tampere</s2>
<s3>FIN</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Astola, Jaakko" sort="Astola, Jaakko" uniqKey="Astola J" first="Jaakko" last="Astola">Jaakko Astola</name>
<affiliation><inist:fA14 i1="01"><s1>Institute of Signal Processing, Tampere University of Technology, P. O. Box 553</s1>
<s2>33101 Tampere</s2>
<s3>FIN</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">04-0486698</idno>
<date when="2004">2004</date>
<idno type="stanalyst">PASCAL 04-0486698 INIST</idno>
<idno type="RBID">Pascal:04-0486698</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000527</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Feature extraction by best anisotropic Haar bases in an OCR system</title>
<author><name sortKey="Gotchev, Atanas" sort="Gotchev, Atanas" uniqKey="Gotchev A" first="Atanas" last="Gotchev">Atanas Gotchev</name>
<affiliation><inist:fA14 i1="01"><s1>Institute of Signal Processing, Tampere University of Technology, P. O. Box 553</s1>
<s2>33101 Tampere</s2>
<s3>FIN</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Rusanovskyy, Dmytro" sort="Rusanovskyy, Dmytro" uniqKey="Rusanovskyy D" first="Dmytro" last="Rusanovskyy">Dmytro Rusanovskyy</name>
<affiliation><inist:fA14 i1="01"><s1>Institute of Signal Processing, Tampere University of Technology, P. O. Box 553</s1>
<s2>33101 Tampere</s2>
<s3>FIN</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Popov, Roumen" sort="Popov, Roumen" uniqKey="Popov R" first="Roumen" last="Popov">Roumen Popov</name>
<affiliation><inist:fA14 i1="02"><s1>Nokia Research Center, Nokia Group, Summit Avenue</s1>
<s2>Farnborough, Hampshire</s2>
<s3>GBR</s3>
<sZ>3 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Egiazarian, Karen" sort="Egiazarian, Karen" uniqKey="Egiazarian K" first="Karen" last="Egiazarian">Karen Egiazarian</name>
<affiliation><inist:fA14 i1="01"><s1>Institute of Signal Processing, Tampere University of Technology, P. O. Box 553</s1>
<s2>33101 Tampere</s2>
<s3>FIN</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Astola, Jaakko" sort="Astola, Jaakko" uniqKey="Astola J" first="Jaakko" last="Astola">Jaakko Astola</name>
<affiliation><inist:fA14 i1="01"><s1>Institute of Signal Processing, Tampere University of Technology, P. O. Box 553</s1>
<s2>33101 Tampere</s2>
<s3>FIN</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
</analytic>
<series><title level="j" type="main">SPIE proceedings series</title>
<idno type="ISSN">1017-2653</idno>
<imprint><date when="2004">2004</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><title level="j" type="main">SPIE proceedings series</title>
<idno type="ISSN">1017-2653</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Character recognition</term>
<term>Database</term>
<term>Feature extraction</term>
<term>Haar function</term>
<term>Image quality</term>
<term>Image resolution</term>
<term>Low resolution</term>
<term>Noisy image</term>
<term>Optical character recognition</term>
<term>Pattern recognition</term>
<term>Search algorithm</term>
<term>Signal processing</term>
<term>Television</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Extraction caractéristique</term>
<term>Fonction Haar</term>
<term>Reconnaissance optique caractère</term>
<term>Reconnaissance caractère</term>
<term>Algorithme recherche</term>
<term>Basse résolution</term>
<term>Résolution image</term>
<term>Image bruitée</term>
<term>Télévision</term>
<term>Base donnée</term>
<term>Traitement signal</term>
<term>Reconnaissance forme</term>
<term>Qualité image</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">In this contribution, we explore the best basis paradigm for in feature extraction. According to this paradigm, a library of bases is built and the best basis is found for a given signal class with respect to some cost measure. We aim at constructing a library of anisotropic bases that are suitable for the class of 2-D binarized character images. We consider two, a dyadic and a non-dyadic generalization scheme of the Haar wavelet packets that lead to anisotropic bases. For the non-dyadic case, generalized Fibonacci p-trees are used to derive the space division structure of the transform. Both schemes allow for an efficient O(N log N) best basis search algorithm. The so built extended library of anisotropic Haar bases is used in the problem of optical character recognition. A special case, namely recognition of characters from very low resolution, noisy TV images is investigated. The best Haar basis found is then used in the feature extraction stage of a standard OCR system. We achieve very promising recognition rates for experimental databases of synthetic and real images separated into 59 classes.</div>
</front>
</TEI>
<inist><standard h6="B"><pA><fA01 i1="01" i2="1"><s0>1017-2653</s0>
</fA01>
<fA05><s2>5298</s2>
</fA05>
<fA08 i1="01" i2="1" l="ENG"><s1>Feature extraction by best anisotropic Haar bases in an OCR system</s1>
</fA08>
<fA09 i1="01" i2="1" l="ENG"><s1>Image processing : algorithms and systems III : San Jose CA, 19-21 January 2004</s1>
</fA09>
<fA11 i1="01" i2="1"><s1>GOTCHEV (Atanas)</s1>
</fA11>
<fA11 i1="02" i2="1"><s1>RUSANOVSKYY (Dmytro)</s1>
</fA11>
<fA11 i1="03" i2="1"><s1>POPOV (Roumen)</s1>
</fA11>
<fA11 i1="04" i2="1"><s1>EGIAZARIAN (Karen)</s1>
</fA11>
<fA11 i1="05" i2="1"><s1>ASTOLA (Jaakko)</s1>
</fA11>
<fA12 i1="01" i2="1"><s1>DOUGHERTY (Edward R.)</s1>
<s9>ed.</s9>
</fA12>
<fA12 i1="02" i2="1"><s1>ASTOLA (Jaakko T.)</s1>
<s9>ed.</s9>
</fA12>
<fA12 i1="03" i2="1"><s1>EGIAZARIAN (Karen O.)</s1>
<s9>ed.</s9>
</fA12>
<fA14 i1="01"><s1>Institute of Signal Processing, Tampere University of Technology, P. O. Box 553</s1>
<s2>33101 Tampere</s2>
<s3>FIN</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
</fA14>
<fA14 i1="02"><s1>Nokia Research Center, Nokia Group, Summit Avenue</s1>
<s2>Farnborough, Hampshire</s2>
<s3>GBR</s3>
<sZ>3 aut.</sZ>
</fA14>
<fA18 i1="01" i2="1"><s1>International Society for Optical Engineering</s1>
<s2>Bellingham WA</s2>
<s3>USA</s3>
<s9>patr.</s9>
</fA18>
<fA20><s1>504-515</s1>
</fA20>
<fA21><s1>2004</s1>
</fA21>
<fA23 i1="01"><s0>ENG</s0>
</fA23>
<fA26 i1="01"><s0>0-8194-5201-7</s0>
</fA26>
<fA43 i1="01"><s1>INIST</s1>
<s2>21760</s2>
<s5>354000124323740530</s5>
</fA43>
<fA44><s0>0000</s0>
<s1>© 2004 INIST-CNRS. All rights reserved.</s1>
</fA44>
<fA45><s0>9 ref.</s0>
</fA45>
<fA47 i1="01" i2="1"><s0>04-0486698</s0>
</fA47>
<fA60><s1>P</s1>
<s2>C</s2>
</fA60>
<fA61><s0>A</s0>
</fA61>
<fA64 i1="01" i2="1"><s0>SPIE proceedings series</s0>
</fA64>
<fA66 i1="01"><s0>USA</s0>
</fA66>
<fC01 i1="01" l="ENG"><s0>In this contribution, we explore the best basis paradigm for in feature extraction. According to this paradigm, a library of bases is built and the best basis is found for a given signal class with respect to some cost measure. We aim at constructing a library of anisotropic bases that are suitable for the class of 2-D binarized character images. We consider two, a dyadic and a non-dyadic generalization scheme of the Haar wavelet packets that lead to anisotropic bases. For the non-dyadic case, generalized Fibonacci p-trees are used to derive the space division structure of the transform. Both schemes allow for an efficient O(N log N) best basis search algorithm. The so built extended library of anisotropic Haar bases is used in the problem of optical character recognition. A special case, namely recognition of characters from very low resolution, noisy TV images is investigated. The best Haar basis found is then used in the feature extraction stage of a standard OCR system. We achieve very promising recognition rates for experimental databases of synthetic and real images separated into 59 classes.</s0>
</fC01>
<fC02 i1="01" i2="X"><s0>001D04A05A</s0>
</fC02>
<fC02 i1="02" i2="X"><s0>001D04A04A2</s0>
</fC02>
<fC03 i1="01" i2="3" l="FRE"><s0>Extraction caractéristique</s0>
<s5>01</s5>
</fC03>
<fC03 i1="01" i2="3" l="ENG"><s0>Feature extraction</s0>
<s5>01</s5>
</fC03>
<fC03 i1="02" i2="X" l="FRE"><s0>Fonction Haar</s0>
<s5>02</s5>
</fC03>
<fC03 i1="02" i2="X" l="ENG"><s0>Haar function</s0>
<s5>02</s5>
</fC03>
<fC03 i1="02" i2="X" l="SPA"><s0>Función Haar</s0>
<s5>02</s5>
</fC03>
<fC03 i1="03" i2="X" l="FRE"><s0>Reconnaissance optique caractère</s0>
<s5>03</s5>
</fC03>
<fC03 i1="03" i2="X" l="ENG"><s0>Optical character recognition</s0>
<s5>03</s5>
</fC03>
<fC03 i1="03" i2="X" l="SPA"><s0>Reconocimento óptico de caracteres</s0>
<s5>03</s5>
</fC03>
<fC03 i1="04" i2="X" l="FRE"><s0>Reconnaissance caractère</s0>
<s5>04</s5>
</fC03>
<fC03 i1="04" i2="X" l="ENG"><s0>Character recognition</s0>
<s5>04</s5>
</fC03>
<fC03 i1="04" i2="X" l="SPA"><s0>Reconocimiento carácter</s0>
<s5>04</s5>
</fC03>
<fC03 i1="05" i2="X" l="FRE"><s0>Algorithme recherche</s0>
<s5>05</s5>
</fC03>
<fC03 i1="05" i2="X" l="ENG"><s0>Search algorithm</s0>
<s5>05</s5>
</fC03>
<fC03 i1="05" i2="X" l="SPA"><s0>Algoritmo búsqueda</s0>
<s5>05</s5>
</fC03>
<fC03 i1="06" i2="X" l="FRE"><s0>Basse résolution</s0>
<s5>06</s5>
</fC03>
<fC03 i1="06" i2="X" l="ENG"><s0>Low resolution</s0>
<s5>06</s5>
</fC03>
<fC03 i1="06" i2="X" l="SPA"><s0>Baja resolución</s0>
<s5>06</s5>
</fC03>
<fC03 i1="07" i2="3" l="FRE"><s0>Résolution image</s0>
<s5>07</s5>
</fC03>
<fC03 i1="07" i2="3" l="ENG"><s0>Image resolution</s0>
<s5>07</s5>
</fC03>
<fC03 i1="08" i2="X" l="FRE"><s0>Image bruitée</s0>
<s5>08</s5>
</fC03>
<fC03 i1="08" i2="X" l="ENG"><s0>Noisy image</s0>
<s5>08</s5>
</fC03>
<fC03 i1="08" i2="X" l="SPA"><s0>Imagen sonora</s0>
<s5>08</s5>
</fC03>
<fC03 i1="09" i2="X" l="FRE"><s0>Télévision</s0>
<s5>09</s5>
</fC03>
<fC03 i1="09" i2="X" l="ENG"><s0>Television</s0>
<s5>09</s5>
</fC03>
<fC03 i1="09" i2="X" l="SPA"><s0>Televisión</s0>
<s5>09</s5>
</fC03>
<fC03 i1="10" i2="X" l="FRE"><s0>Base donnée</s0>
<s5>10</s5>
</fC03>
<fC03 i1="10" i2="X" l="ENG"><s0>Database</s0>
<s5>10</s5>
</fC03>
<fC03 i1="10" i2="X" l="SPA"><s0>Base dato</s0>
<s5>10</s5>
</fC03>
<fC03 i1="11" i2="X" l="FRE"><s0>Traitement signal</s0>
<s5>11</s5>
</fC03>
<fC03 i1="11" i2="X" l="ENG"><s0>Signal processing</s0>
<s5>11</s5>
</fC03>
<fC03 i1="11" i2="X" l="SPA"><s0>Procesamiento señal</s0>
<s5>11</s5>
</fC03>
<fC03 i1="12" i2="X" l="FRE"><s0>Reconnaissance forme</s0>
<s5>12</s5>
</fC03>
<fC03 i1="12" i2="X" l="ENG"><s0>Pattern recognition</s0>
<s5>12</s5>
</fC03>
<fC03 i1="12" i2="X" l="SPA"><s0>Reconocimiento patrón</s0>
<s5>12</s5>
</fC03>
<fC03 i1="13" i2="X" l="FRE"><s0>Qualité image</s0>
<s5>13</s5>
</fC03>
<fC03 i1="13" i2="X" l="ENG"><s0>Image quality</s0>
<s5>13</s5>
</fC03>
<fC03 i1="13" i2="X" l="SPA"><s0>Calidad imagen</s0>
<s5>13</s5>
</fC03>
<fN21><s1>278</s1>
</fN21>
<fN44 i1="01"><s1>OTO</s1>
</fN44>
<fN82><s1>OTO</s1>
</fN82>
</pA>
<pR><fA30 i1="01" i2="1" l="ENG"><s1>Image processing : algorithms and systems. Conference</s1>
<s2>3</s2>
<s3>San Jose CA USA</s3>
<s4>2004-01-19</s4>
</fA30>
</pR>
</standard>
<server><NO>PASCAL 04-0486698 INIST</NO>
<ET>Feature extraction by best anisotropic Haar bases in an OCR system</ET>
<AU>GOTCHEV (Atanas); RUSANOVSKYY (Dmytro); POPOV (Roumen); EGIAZARIAN (Karen); ASTOLA (Jaakko); DOUGHERTY (Edward R.); ASTOLA (Jaakko T.); EGIAZARIAN (Karen O.)</AU>
<AF>Institute of Signal Processing, Tampere University of Technology, P. O. Box 553/33101 Tampere/Finlande (1 aut., 2 aut., 4 aut., 5 aut.); Nokia Research Center, Nokia Group, Summit Avenue/Farnborough, Hampshire/Royaume-Uni (3 aut.)</AF>
<DT>Publication en série; Congrès; Niveau analytique</DT>
<SO>SPIE proceedings series; ISSN 1017-2653; Etats-Unis; Da. 2004; Vol. 5298; Pp. 504-515; Bibl. 9 ref.</SO>
<LA>Anglais</LA>
<EA>In this contribution, we explore the best basis paradigm for in feature extraction. According to this paradigm, a library of bases is built and the best basis is found for a given signal class with respect to some cost measure. We aim at constructing a library of anisotropic bases that are suitable for the class of 2-D binarized character images. We consider two, a dyadic and a non-dyadic generalization scheme of the Haar wavelet packets that lead to anisotropic bases. For the non-dyadic case, generalized Fibonacci p-trees are used to derive the space division structure of the transform. Both schemes allow for an efficient O(N log N) best basis search algorithm. The so built extended library of anisotropic Haar bases is used in the problem of optical character recognition. A special case, namely recognition of characters from very low resolution, noisy TV images is investigated. The best Haar basis found is then used in the feature extraction stage of a standard OCR system. We achieve very promising recognition rates for experimental databases of synthetic and real images separated into 59 classes.</EA>
<CC>001D04A05A; 001D04A04A2</CC>
<FD>Extraction caractéristique; Fonction Haar; Reconnaissance optique caractère; Reconnaissance caractère; Algorithme recherche; Basse résolution; Résolution image; Image bruitée; Télévision; Base donnée; Traitement signal; Reconnaissance forme; Qualité image</FD>
<ED>Feature extraction; Haar function; Optical character recognition; Character recognition; Search algorithm; Low resolution; Image resolution; Noisy image; Television; Database; Signal processing; Pattern recognition; Image quality</ED>
<SD>Función Haar; Reconocimento óptico de caracteres; Reconocimiento carácter; Algoritmo búsqueda; Baja resolución; Imagen sonora; Televisión; Base dato; Procesamiento señal; Reconocimiento patrón; Calidad imagen</SD>
<LO>INIST-21760.354000124323740530</LO>
<ID>04-0486698</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 000527 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/PascalFrancis/Corpus/biblio.hfd -nk 000527 | 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:04-0486698 |texte= Feature extraction by best anisotropic Haar bases in an OCR system }}
This area was generated with Dilib version V0.6.32. |