How to Deal with Uncertainty and Variability: Experience and Solutions
Identifieur interne : 000C26 ( Main/Exploration ); précédent : 000C25; suivant : 000C27How to Deal with Uncertainty and Variability: Experience and Solutions
Auteurs : Hiromichi Fujisawa [Japon]Source :
- Lecture Notes in Computer Science [ 0302-9743 ] ; 2008.
Abstract
Abstract: Uncertainty and variability are two of the most important concepts at the center of pattern recognition. It is especially true when patterns to be recognized are complex in nature and not controlled by any artificial constraints. Handwritten postal address recognition is one such case. This paper presents five principles of dealing with uncertainty and variability, and discusses how to decompose the complex recognition task into manageable sub-tasks. When applicable, block diagrams will clarify the structure of various recognition components. This paper also presents implementation of those principles into real recognition engines. It will demonstrate that high accuracy and robustness of a recognition system, which relates to uncertainty and variability, respectively, can occur only with comprehensive approaches.
Url:
DOI: 10.1007/978-3-540-78199-8_8
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 001648
- to stream Istex, to step Curation: 001555
- to stream Istex, to step Checkpoint: 000693
- to stream Main, to step Merge: 000C38
- to stream Main, to step Curation: 000C26
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">How to Deal with Uncertainty and Variability: Experience and Solutions</title><author><name sortKey="Fujisawa, Hiromichi" sort="Fujisawa, Hiromichi" uniqKey="Fujisawa H" first="Hiromichi" last="Fujisawa">Hiromichi Fujisawa</name></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:59EEE88DF3AB365D6721EFCC43A204161F949973</idno><date when="2008" year="2008">2008</date><idno type="doi">10.1007/978-3-540-78199-8_8</idno><idno type="url">https://api.istex.fr/document/59EEE88DF3AB365D6721EFCC43A204161F949973/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">001648</idno><idno type="wicri:Area/Istex/Curation">001555</idno><idno type="wicri:Area/Istex/Checkpoint">000693</idno><idno type="wicri:doubleKey">0302-9743:2008:Fujisawa H:how:to:deal</idno><idno type="wicri:Area/Main/Merge">000C38</idno><idno type="wicri:Area/Main/Curation">000C26</idno><idno type="wicri:Area/Main/Exploration">000C26</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">How to Deal with Uncertainty and Variability: Experience and Solutions</title><author><name sortKey="Fujisawa, Hiromichi" sort="Fujisawa, Hiromichi" uniqKey="Fujisawa H" first="Hiromichi" last="Fujisawa">Hiromichi Fujisawa</name><affiliation wicri:level="3"><country xml:lang="fr">Japon</country><wicri:regionArea>Central Research Laboratory, Hitachi, Ltd., 185-8601, Tokyo</wicri:regionArea><placeName><settlement type="city">Tokyo</settlement></placeName></affiliation><affiliation><wicri:noCountry code="no comma">E-mail: hiromichi.fujisawa.sb@hitachi.com</wicri:noCountry></affiliation></author></analytic><monogr></monogr><series><title level="s">Lecture Notes in Computer Science</title><imprint><date>2008</date></imprint><idno type="ISSN">0302-9743</idno><idno type="eISSN">1611-3349</idno><idno type="ISSN">0302-9743</idno></series><idno type="istex">59EEE88DF3AB365D6721EFCC43A204161F949973</idno><idno type="DOI">10.1007/978-3-540-78199-8_8</idno><idno type="ChapterID">8</idno><idno type="ChapterID">Chap8</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: Uncertainty and variability are two of the most important concepts at the center of pattern recognition. It is especially true when patterns to be recognized are complex in nature and not controlled by any artificial constraints. Handwritten postal address recognition is one such case. This paper presents five principles of dealing with uncertainty and variability, and discusses how to decompose the complex recognition task into manageable sub-tasks. When applicable, block diagrams will clarify the structure of various recognition components. This paper also presents implementation of those principles into real recognition engines. It will demonstrate that high accuracy and robustness of a recognition system, which relates to uncertainty and variability, respectively, can occur only with comprehensive approaches.</div></front></TEI><affiliations><list><country><li>Japon</li></country><settlement><li>Tokyo</li></settlement></list><tree><country name="Japon"><noRegion><name sortKey="Fujisawa, Hiromichi" sort="Fujisawa, Hiromichi" uniqKey="Fujisawa H" first="Hiromichi" last="Fujisawa">Hiromichi Fujisawa</name></noRegion></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 000C26 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000C26 | 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:59EEE88DF3AB365D6721EFCC43A204161F949973
|texte= How to Deal with Uncertainty and Variability: Experience and Solutions
}}
| This area was generated with Dilib version V0.6.32. |  |