A Novel Fusion of Holistic and Analytical Paradigms for the Recognition of Handwritten Address Fields
Identifieur interne : 001D41 ( Main/Merge ); précédent : 001D40; suivant : 001D42A Novel Fusion of Holistic and Analytical Paradigms for the Recognition of Handwritten Address Fields
Auteurs : Keong Lee [Singapour] ; Graham Leedham [Singapour]Source :
- Lecture Notes in Computer Science [ 0302-9743 ] ; 2000.
Abstract
Abstract: A novel scheme of automatic address interpretation for the recognition of unconstrained address fields is presented in this paper. This hybrid method fuses a holistic paradigm with an analytical approach to handwritten word recognition for an identifiable address field, such as building number, to reduce the error and rejection rates. The holistic paradigm uses fuzzy membership, interclass distance measures in feature selection and extraction using the Minkowski metric of order s=2, dynamic lexicon and linear programming techniques. The method was evaluated using a set of 900 binary postal images, which contain a mixture of purely cursive and touching discrete addresses. Given the image of a handwritten address, our algorithm produced a cost-effective delivery point code where 72% of the mail-pieces were correctly encoded and 28% were rejected. The error rate was zero on this test set.
Url:
DOI: 10.1007/3-540-45049-1_59
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 000723
- to stream Istex, to step Curation: 000715
- to stream Istex, to step Checkpoint: 001244
Links to Exploration step
ISTEX:AB6C01E3BD2C09F6641AF4F0E84000B4A84588D7Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct:series"><teiHeader><fileDesc><titleStmt><title xml:lang="en">A Novel Fusion of Holistic and Analytical Paradigms for the Recognition of Handwritten Address Fields</title>
<author><name sortKey="Lee, Keong" sort="Lee, Keong" uniqKey="Lee K" first="Keong" last="Lee">Keong Lee</name>
</author>
<author><name sortKey="Leedham, Graham" sort="Leedham, Graham" uniqKey="Leedham G" first="Graham" last="Leedham">Graham Leedham</name>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">ISTEX</idno>
<idno type="RBID">ISTEX:AB6C01E3BD2C09F6641AF4F0E84000B4A84588D7</idno>
<date when="2000" year="2000">2000</date>
<idno type="doi">10.1007/3-540-45049-1_59</idno>
<idno type="url">https://api.istex.fr/document/AB6C01E3BD2C09F6641AF4F0E84000B4A84588D7/fulltext/pdf</idno>
<idno type="wicri:Area/Istex/Corpus">000723</idno>
<idno type="wicri:Area/Istex/Curation">000715</idno>
<idno type="wicri:Area/Istex/Checkpoint">001244</idno>
<idno type="wicri:doubleKey">0302-9743:2000:Lee K:a:novel:fusion</idno>
<idno type="wicri:Area/Main/Merge">001D41</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">A Novel Fusion of Holistic and Analytical Paradigms for the Recognition of Handwritten Address Fields</title>
<author><name sortKey="Lee, Keong" sort="Lee, Keong" uniqKey="Lee K" first="Keong" last="Lee">Keong Lee</name>
<affiliation wicri:level="1"><country xml:lang="fr">Singapour</country>
<wicri:regionArea>School of Applied Science, Nanyang Technological University, N4-02a-32 Nanyang Avenue, 639798</wicri:regionArea>
<wicri:noRegion>639798</wicri:noRegion>
</affiliation>
<affiliation><wicri:noCountry code="no comma">E-mail: Travck@yahoo.com</wicri:noCountry>
</affiliation>
</author>
<author><name sortKey="Leedham, Graham" sort="Leedham, Graham" uniqKey="Leedham G" first="Graham" last="Leedham">Graham Leedham</name>
<affiliation wicri:level="1"><country xml:lang="fr">Singapour</country>
<wicri:regionArea>School of Applied Science, Nanyang Technological University, N4-02a-32 Nanyang Avenue, 639798</wicri:regionArea>
<wicri:noRegion>639798</wicri:noRegion>
</affiliation>
<affiliation wicri:level="1"><country wicri:rule="url">Singapour</country>
</affiliation>
</author>
</analytic>
<monogr></monogr>
<series><title level="s">Lecture Notes in Computer Science</title>
<imprint><date>2000</date>
</imprint>
<idno type="ISSN">0302-9743</idno>
<idno type="ISSN">0302-9743</idno>
</series>
<idno type="istex">AB6C01E3BD2C09F6641AF4F0E84000B4A84588D7</idno>
<idno type="DOI">10.1007/3-540-45049-1_59</idno>
<idno type="ChapterID">59</idno>
<idno type="ChapterID">Chap59</idno>
</biblStruct>
</sourceDesc>
<seriesStmt><idno type="ISSN">0302-9743</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass></textClass>
<langUsage><language ident="en">en</language>
</langUsage>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">Abstract: A novel scheme of automatic address interpretation for the recognition of unconstrained address fields is presented in this paper. This hybrid method fuses a holistic paradigm with an analytical approach to handwritten word recognition for an identifiable address field, such as building number, to reduce the error and rejection rates. The holistic paradigm uses fuzzy membership, interclass distance measures in feature selection and extraction using the Minkowski metric of order s=2, dynamic lexicon and linear programming techniques. The method was evaluated using a set of 900 binary postal images, which contain a mixture of purely cursive and touching discrete addresses. Given the image of a handwritten address, our algorithm produced a cost-effective delivery point code where 72% of the mail-pieces were correctly encoded and 28% were rejected. The error rate was zero on this test set.</div>
</front>
</TEI>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/Main/Merge
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 001D41 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Merge/biblio.hfd -nk 001D41 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Ticri/CIDE |area= OcrV1 |flux= Main |étape= Merge |type= RBID |clé= ISTEX:AB6C01E3BD2C09F6641AF4F0E84000B4A84588D7 |texte= A Novel Fusion of Holistic and Analytical Paradigms for the Recognition of Handwritten Address Fields }}
This area was generated with Dilib version V0.6.32. |