A fuzzy graph theoretic approach to recognize the totally unconstrained handwritten numerals
Identifieur interne : 003030 ( Main/Exploration ); précédent : 003029; suivant : 003031A fuzzy graph theoretic approach to recognize the totally unconstrained handwritten numerals
Auteurs : I. S. I Abuhaiba [Arabie saoudite] ; P. Ahmed [Arabie saoudite]Source :
- Pattern Recognition [ 0031-3203 ] ; 1993.
Abstract
An automatic off-line character recognition system for totally unconstrained handwritten numerals is presented. The system was trained and tested on the field data collected by the U.S. Postal Services Department from dead letter envelopes. It was trained on 1763 unnormalized samples. The training process produced a feasible set of 105 Fuzzy Constrained Character Graph Models (FCCGMs). FCCGMs tolerate large variability in size, shape and writing style. Characters were recognized by applying a set of rules to match a character tree representation to a FCCGM. A character tree is obtained by first converting the character skeleton into an approximate polygon and then transforming the polygon into a tree structure suitable for recognition purposes. The system was tested on (not including the training set) 1812 unnormalized samples and it proved to be powerful in recognition rate and tolerance to multi-writer, multi-pen, multi-textured paper, and multi-color ink. Reliability, recognition, substitution error, and rejection rates of the system are 97.1, 90.7, 2.9, and 6.4%, respectively.
Url:
DOI: 10.1016/0031-3203(93)90139-N
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 000855
- to stream Istex, to step Curation: 000845
- to stream Istex, to step Checkpoint: 002290
- to stream Main, to step Merge: 003201
- to stream Main, to step Curation: 003030
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title>A fuzzy graph theoretic approach to recognize the totally unconstrained handwritten numerals</title><author><name sortKey="Abuhaiba, I S I" sort="Abuhaiba, I S I" uniqKey="Abuhaiba I" first="I. S. I" last="Abuhaiba">I. S. I Abuhaiba</name></author><author><name sortKey="Ahmed, P" sort="Ahmed, P" uniqKey="Ahmed P" first="P" last="Ahmed">P. Ahmed</name></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:92EFC3A08D7C71A70CE4ED25A13C878B33D5DA44</idno><date when="1993" year="1993">1993</date><idno type="doi">10.1016/0031-3203(93)90139-N</idno><idno type="url">https://api.istex.fr/document/92EFC3A08D7C71A70CE4ED25A13C878B33D5DA44/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">000855</idno><idno type="wicri:Area/Istex/Curation">000845</idno><idno type="wicri:Area/Istex/Checkpoint">002290</idno><idno type="wicri:doubleKey">0031-3203:1993:Abuhaiba I:a:fuzzy:graph</idno><idno type="wicri:Area/Main/Merge">003201</idno><idno type="wicri:Area/Main/Curation">003030</idno><idno type="wicri:Area/Main/Exploration">003030</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a">A fuzzy graph theoretic approach to recognize the totally unconstrained handwritten numerals</title><author><name sortKey="Abuhaiba, I S I" sort="Abuhaiba, I S I" uniqKey="Abuhaiba I" first="I. S. I" last="Abuhaiba">I. S. I Abuhaiba</name><affiliation wicri:level="1"><country xml:lang="fr">Arabie saoudite</country><wicri:regionArea>P.O. Box 89591, Riyadh 11692</wicri:regionArea><wicri:noRegion>Riyadh 11692</wicri:noRegion></affiliation></author><author><name sortKey="Ahmed, P" sort="Ahmed, P" uniqKey="Ahmed P" first="P" last="Ahmed">P. Ahmed</name><affiliation wicri:level="1"><country xml:lang="fr">Arabie saoudite</country><wicri:regionArea>Department of Computer Science, CCIS, King Saud University, P.O. Box 51178, Riyadh 11543</wicri:regionArea><wicri:noRegion>Riyadh 11543</wicri:noRegion></affiliation></author></analytic><monogr></monogr><series><title level="j">Pattern Recognition</title><title level="j" type="abbrev">PR</title><idno type="ISSN">0031-3203</idno><imprint><publisher>ELSEVIER</publisher><date type="published" when="1993">1993</date><biblScope unit="volume">26</biblScope><biblScope unit="issue">9</biblScope><biblScope unit="page" from="1335">1335</biblScope><biblScope unit="page" to="1350">1350</biblScope></imprint><idno type="ISSN">0031-3203</idno></series><idno type="istex">92EFC3A08D7C71A70CE4ED25A13C878B33D5DA44</idno><idno type="DOI">10.1016/0031-3203(93)90139-N</idno><idno type="PII">0031-3203(93)90139-N</idno></biblStruct></sourceDesc><seriesStmt><idno type="ISSN">0031-3203</idno></seriesStmt></fileDesc><profileDesc><textClass></textClass><langUsage><language ident="en">en</language></langUsage></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">An automatic off-line character recognition system for totally unconstrained handwritten numerals is presented. The system was trained and tested on the field data collected by the U.S. Postal Services Department from dead letter envelopes. It was trained on 1763 unnormalized samples. The training process produced a feasible set of 105 Fuzzy Constrained Character Graph Models (FCCGMs). FCCGMs tolerate large variability in size, shape and writing style. Characters were recognized by applying a set of rules to match a character tree representation to a FCCGM. A character tree is obtained by first converting the character skeleton into an approximate polygon and then transforming the polygon into a tree structure suitable for recognition purposes. The system was tested on (not including the training set) 1812 unnormalized samples and it proved to be powerful in recognition rate and tolerance to multi-writer, multi-pen, multi-textured paper, and multi-color ink. Reliability, recognition, substitution error, and rejection rates of the system are 97.1, 90.7, 2.9, and 6.4%, respectively.</div></front></TEI><affiliations><list><country><li>Arabie saoudite</li></country></list><tree><country name="Arabie saoudite"><noRegion><name sortKey="Abuhaiba, I S I" sort="Abuhaiba, I S I" uniqKey="Abuhaiba I" first="I. S. I" last="Abuhaiba">I. S. I Abuhaiba</name></noRegion><name sortKey="Ahmed, P" sort="Ahmed, P" uniqKey="Ahmed P" first="P" last="Ahmed">P. Ahmed</name></country></tree></affiliations></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 003030 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 003030 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Ticri/CIDE
|area= OcrV1
|flux= Main
|étape= Exploration
|type= RBID
|clé= ISTEX:92EFC3A08D7C71A70CE4ED25A13C878B33D5DA44
|texte= A fuzzy graph theoretic approach to recognize the totally unconstrained handwritten numerals
}}
| This area was generated with Dilib version V0.6.32. |  |