Handwritten Address Recognition Using Hidden Markov Models
Identifieur interne : 001526 ( Main/Exploration ); précédent : 001525; suivant : 001527Handwritten Address Recognition Using Hidden Markov Models
Auteurs : Anja Brakensiek [Allemagne] ; Gerhard Rigoll [Allemagne]Source :
- Lecture Notes in Computer Science [ 0302-9743 ] ; 2004.
Abstract
Abstract: In this paper several aspects of a recognition system for cursive handwritten German address words (cities and streets) are described. The recognition system is based on Hidden Markov Models (HMMs), whereat the focus is on two main problems: the changes in the writing style depending on time or regional differences and the difficulty to select the correct (complete) dictionary for address reading. The first problem leads to the examination of three different adaptation techniques: Maximum Likelihood (ML), Maximum Likelihood Linear Regression (MLLR) and Scaled Likelihood Linear Regression (SLLR). To handle the second problem language models based on backoff character n-grams are examined to evaluate the performance of an open vocabulary recognition (without dictionary). For both problems the determination of confidence measures (based on the frame-normalized likelihood, a garbage model, a two-best recognition or an unconstrained character decoding) is important, either for an unsupervised adaptation or the detection of out of vocabulary words (OOV). The databases, which are used for recognition, are provided by Siemens Dematic (SD) within the Adaptive READ project.
Url:
DOI: 10.1007/978-3-540-24642-8_7
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 002054
- to stream Istex, to step Curation: 001F16
- to stream Istex, to step Checkpoint: 000D61
- to stream Main, to step Merge: 001577
- to stream Main, to step Curation: 001526
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Handwritten Address Recognition Using Hidden Markov Models</title><author><name sortKey="Brakensiek, Anja" sort="Brakensiek, Anja" uniqKey="Brakensiek A" first="Anja" last="Brakensiek">Anja Brakensiek</name></author><author><name sortKey="Rigoll, Gerhard" sort="Rigoll, Gerhard" uniqKey="Rigoll G" first="Gerhard" last="Rigoll">Gerhard Rigoll</name></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:F117579CD161A450A17A412DF7B3E32EAF827FBB</idno><date when="2004" year="2004">2004</date><idno type="doi">10.1007/978-3-540-24642-8_7</idno><idno type="url">https://api.istex.fr/document/F117579CD161A450A17A412DF7B3E32EAF827FBB/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">002054</idno><idno type="wicri:Area/Istex/Curation">001F16</idno><idno type="wicri:Area/Istex/Checkpoint">000D61</idno><idno type="wicri:doubleKey">0302-9743:2004:Brakensiek A:handwritten:address:recognition</idno><idno type="wicri:Area/Main/Merge">001577</idno><idno type="wicri:Area/Main/Curation">001526</idno><idno type="wicri:Area/Main/Exploration">001526</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Handwritten Address Recognition Using Hidden Markov Models</title><author><name sortKey="Brakensiek, Anja" sort="Brakensiek, Anja" uniqKey="Brakensiek A" first="Anja" last="Brakensiek">Anja Brakensiek</name><affiliation wicri:level="1"><country xml:lang="fr">Allemagne</country><wicri:regionArea>Dept. of Computer Science, University Duisburg, 47057, Duisburg</wicri:regionArea><wicri:noRegion>47057, Duisburg</wicri:noRegion><wicri:noRegion>Duisburg</wicri:noRegion></affiliation><affiliation><wicri:noCountry code="no comma">E-mail: anja.brakensiek@odt-oce.com</wicri:noCountry></affiliation></author><author><name sortKey="Rigoll, Gerhard" sort="Rigoll, Gerhard" uniqKey="Rigoll G" first="Gerhard" last="Rigoll">Gerhard Rigoll</name><affiliation wicri:level="1"><country xml:lang="fr">Allemagne</country><wicri:regionArea>Dept. of Computer Science, University Duisburg, 47057, Duisburg</wicri:regionArea><wicri:noRegion>47057, Duisburg</wicri:noRegion><wicri:noRegion>Duisburg</wicri:noRegion></affiliation><affiliation wicri:level="3"><country xml:lang="fr">Allemagne</country><wicri:regionArea>Inst. for Human-Machine Communication, Munich University of Technology, 80290, Munich</wicri:regionArea><placeName><settlement type="city">Munich</settlement><region type="land" nuts="1">Bavière</region><region type="district" nuts="2">District de Haute-Bavière</region></placeName></affiliation><affiliation wicri:level="1"><country wicri:rule="url">Allemagne</country></affiliation></author></analytic><monogr></monogr><series><title level="s">Lecture Notes in Computer Science</title><imprint><date>2004</date></imprint><idno type="ISSN">0302-9743</idno><idno type="eISSN">1611-3349</idno><idno type="ISSN">0302-9743</idno></series><idno type="istex">F117579CD161A450A17A412DF7B3E32EAF827FBB</idno><idno type="DOI">10.1007/978-3-540-24642-8_7</idno><idno type="ChapterID">7</idno><idno type="ChapterID">Chap7</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: In this paper several aspects of a recognition system for cursive handwritten German address words (cities and streets) are described. The recognition system is based on Hidden Markov Models (HMMs), whereat the focus is on two main problems: the changes in the writing style depending on time or regional differences and the difficulty to select the correct (complete) dictionary for address reading. The first problem leads to the examination of three different adaptation techniques: Maximum Likelihood (ML), Maximum Likelihood Linear Regression (MLLR) and Scaled Likelihood Linear Regression (SLLR). To handle the second problem language models based on backoff character n-grams are examined to evaluate the performance of an open vocabulary recognition (without dictionary). For both problems the determination of confidence measures (based on the frame-normalized likelihood, a garbage model, a two-best recognition or an unconstrained character decoding) is important, either for an unsupervised adaptation or the detection of out of vocabulary words (OOV). The databases, which are used for recognition, are provided by Siemens Dematic (SD) within the Adaptive READ project.</div></front></TEI><affiliations><list><country><li>Allemagne</li></country><region><li>Bavière</li><li>District de Haute-Bavière</li></region><settlement><li>Munich</li></settlement></list><tree><country name="Allemagne"><noRegion><name sortKey="Brakensiek, Anja" sort="Brakensiek, Anja" uniqKey="Brakensiek A" first="Anja" last="Brakensiek">Anja Brakensiek</name></noRegion><name sortKey="Rigoll, Gerhard" sort="Rigoll, Gerhard" uniqKey="Rigoll G" first="Gerhard" last="Rigoll">Gerhard Rigoll</name><name sortKey="Rigoll, Gerhard" sort="Rigoll, Gerhard" uniqKey="Rigoll G" first="Gerhard" last="Rigoll">Gerhard Rigoll</name><name sortKey="Rigoll, Gerhard" sort="Rigoll, Gerhard" uniqKey="Rigoll G" first="Gerhard" last="Rigoll">Gerhard Rigoll</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 001526 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 001526 | 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:F117579CD161A450A17A412DF7B3E32EAF827FBB
|texte= Handwritten Address Recognition Using Hidden Markov Models
}}
| This area was generated with Dilib version V0.6.32. |  |