Selecting a restoration technique to minimize OCR error.
Identifieur interne : 000066 ( PubMed/Checkpoint ); précédent : 000065; suivant : 000067Selecting a restoration technique to minimize OCR error.
Auteurs : M. Cannon [États-Unis] ; M. Fugate ; D R Hush ; C. ScovelSource :
- IEEE transactions on neural networks / a publication of the IEEE Neural Networks Council [ 1045-9227 ] ; 2003.
Abstract
This paper introduces a learning problem related to the task of converting printed documents to ASCII text files. The goal of the learning procedure is to produce a function that maps documents to restoration techniques in such a way that on average the restored documents have minimum optical character recognition error. We derive a general form for the optimal function and use it to motivate the development of a nonparametric method based on nearest neighbors. We also develop a direct method of solution based on empirical error minimization for which we prove a finite sample bound on estimation error that is independent of distribution. We show that this empirical error minimization problem is an extension of the empirical optimization problem for traditional M-class classification with general loss function and prove computational hardness for this problem. We then derive a simple iterative algorithm called generalized multiclass ratchet (GMR) and prove that it produces an optimal function asymptotically (with probability 1). To obtain the GMR algorithm we introduce a new data map that extends Kesler's construction for the multiclass problem and then apply an algorithm called Ratchet to this mapped data, where Ratchet is a modification of the Pocket algorithm . Finally, we apply these methods to a collection of documents and report on the experimental results.
DOI: 10.1109/TNN.2003.811711
PubMed: 18238033
Affiliations:
Links toward previous steps (curation, corpus...)
Links to Exploration step
pubmed:18238033Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">Selecting a restoration technique to minimize OCR error.</title>
<author><name sortKey="Cannon, M" sort="Cannon, M" uniqKey="Cannon M" first="M" last="Cannon">M. Cannon</name>
<affiliation wicri:level="2"><nlm:affiliation>Comput. Res. and Applications Group, Los Alamos Nat. Lab., NM, USA.</nlm:affiliation>
<country xml:lang="fr">États-Unis</country>
<wicri:regionArea>Comput. Res. and Applications Group, Los Alamos Nat. Lab., NM</wicri:regionArea>
<placeName><region type="state">Nouveau-Mexique</region>
</placeName>
</affiliation>
</author>
<author><name sortKey="Fugate, M" sort="Fugate, M" uniqKey="Fugate M" first="M" last="Fugate">M. Fugate</name>
</author>
<author><name sortKey="Hush, D R" sort="Hush, D R" uniqKey="Hush D" first="D R" last="Hush">D R Hush</name>
</author>
<author><name sortKey="Scovel, C" sort="Scovel, C" uniqKey="Scovel C" first="C" last="Scovel">C. Scovel</name>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">PubMed</idno>
<date when="2003">2003</date>
<idno type="doi">10.1109/TNN.2003.811711</idno>
<idno type="RBID">pubmed:18238033</idno>
<idno type="pmid">18238033</idno>
<idno type="wicri:Area/PubMed/Corpus">000055</idno>
<idno type="wicri:Area/PubMed/Curation">000055</idno>
<idno type="wicri:Area/PubMed/Checkpoint">000055</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en">Selecting a restoration technique to minimize OCR error.</title>
<author><name sortKey="Cannon, M" sort="Cannon, M" uniqKey="Cannon M" first="M" last="Cannon">M. Cannon</name>
<affiliation wicri:level="2"><nlm:affiliation>Comput. Res. and Applications Group, Los Alamos Nat. Lab., NM, USA.</nlm:affiliation>
<country xml:lang="fr">États-Unis</country>
<wicri:regionArea>Comput. Res. and Applications Group, Los Alamos Nat. Lab., NM</wicri:regionArea>
<placeName><region type="state">Nouveau-Mexique</region>
</placeName>
</affiliation>
</author>
<author><name sortKey="Fugate, M" sort="Fugate, M" uniqKey="Fugate M" first="M" last="Fugate">M. Fugate</name>
</author>
<author><name sortKey="Hush, D R" sort="Hush, D R" uniqKey="Hush D" first="D R" last="Hush">D R Hush</name>
</author>
<author><name sortKey="Scovel, C" sort="Scovel, C" uniqKey="Scovel C" first="C" last="Scovel">C. Scovel</name>
</author>
</analytic>
<series><title level="j">IEEE transactions on neural networks / a publication of the IEEE Neural Networks Council</title>
<idno type="ISSN">1045-9227</idno>
<imprint><date when="2003" type="published">2003</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><textClass></textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">This paper introduces a learning problem related to the task of converting printed documents to ASCII text files. The goal of the learning procedure is to produce a function that maps documents to restoration techniques in such a way that on average the restored documents have minimum optical character recognition error. We derive a general form for the optimal function and use it to motivate the development of a nonparametric method based on nearest neighbors. We also develop a direct method of solution based on empirical error minimization for which we prove a finite sample bound on estimation error that is independent of distribution. We show that this empirical error minimization problem is an extension of the empirical optimization problem for traditional M-class classification with general loss function and prove computational hardness for this problem. We then derive a simple iterative algorithm called generalized multiclass ratchet (GMR) and prove that it produces an optimal function asymptotically (with probability 1). To obtain the GMR algorithm we introduce a new data map that extends Kesler's construction for the multiclass problem and then apply an algorithm called Ratchet to this mapped data, where Ratchet is a modification of the Pocket algorithm . Finally, we apply these methods to a collection of documents and report on the experimental results.</div>
</front>
</TEI>
<pubmed><MedlineCitation Owner="NLM" Status="PubMed-not-MEDLINE"><PMID Version="1">18238033</PMID>
<DateCreated><Year>2008</Year>
<Month>02</Month>
<Day>01</Day>
</DateCreated>
<DateCompleted><Year>2012</Year>
<Month>10</Month>
<Day>02</Day>
</DateCompleted>
<Article PubModel="Print"><Journal><ISSN IssnType="Print">1045-9227</ISSN>
<JournalIssue CitedMedium="Print"><Volume>14</Volume>
<Issue>3</Issue>
<PubDate><Year>2003</Year>
</PubDate>
</JournalIssue>
<Title>IEEE transactions on neural networks / a publication of the IEEE Neural Networks Council</Title>
<ISOAbbreviation>IEEE Trans Neural Netw</ISOAbbreviation>
</Journal>
<ArticleTitle>Selecting a restoration technique to minimize OCR error.</ArticleTitle>
<Pagination><MedlinePgn>478-90</MedlinePgn>
</Pagination>
<ELocationID EIdType="doi" ValidYN="Y">10.1109/TNN.2003.811711</ELocationID>
<Abstract><AbstractText>This paper introduces a learning problem related to the task of converting printed documents to ASCII text files. The goal of the learning procedure is to produce a function that maps documents to restoration techniques in such a way that on average the restored documents have minimum optical character recognition error. We derive a general form for the optimal function and use it to motivate the development of a nonparametric method based on nearest neighbors. We also develop a direct method of solution based on empirical error minimization for which we prove a finite sample bound on estimation error that is independent of distribution. We show that this empirical error minimization problem is an extension of the empirical optimization problem for traditional M-class classification with general loss function and prove computational hardness for this problem. We then derive a simple iterative algorithm called generalized multiclass ratchet (GMR) and prove that it produces an optimal function asymptotically (with probability 1). To obtain the GMR algorithm we introduce a new data map that extends Kesler's construction for the multiclass problem and then apply an algorithm called Ratchet to this mapped data, where Ratchet is a modification of the Pocket algorithm . Finally, we apply these methods to a collection of documents and report on the experimental results.</AbstractText>
</Abstract>
<AuthorList CompleteYN="Y"><Author ValidYN="Y"><LastName>Cannon</LastName>
<ForeName>M</ForeName>
<Initials>M</Initials>
<AffiliationInfo><Affiliation>Comput. Res. and Applications Group, Los Alamos Nat. Lab., NM, USA.</Affiliation>
</AffiliationInfo>
</Author>
<Author ValidYN="Y"><LastName>Fugate</LastName>
<ForeName>M</ForeName>
<Initials>M</Initials>
</Author>
<Author ValidYN="Y"><LastName>Hush</LastName>
<ForeName>D R</ForeName>
<Initials>DR</Initials>
</Author>
<Author ValidYN="Y"><LastName>Scovel</LastName>
<ForeName>C</ForeName>
<Initials>C</Initials>
</Author>
</AuthorList>
<Language>eng</Language>
<PublicationTypeList><PublicationType UI="D016428">Journal Article</PublicationType>
</PublicationTypeList>
</Article>
<MedlineJournalInfo><Country>United States</Country>
<MedlineTA>IEEE Trans Neural Netw</MedlineTA>
<NlmUniqueID>101211035</NlmUniqueID>
<ISSNLinking>1045-9227</ISSNLinking>
</MedlineJournalInfo>
</MedlineCitation>
<PubmedData><History><PubMedPubDate PubStatus="pubmed"><Year>2008</Year>
<Month>2</Month>
<Day>2</Day>
<Hour>9</Hour>
<Minute>0</Minute>
</PubMedPubDate>
<PubMedPubDate PubStatus="medline"><Year>2008</Year>
<Month>2</Month>
<Day>2</Day>
<Hour>9</Hour>
<Minute>1</Minute>
</PubMedPubDate>
<PubMedPubDate PubStatus="entrez"><Year>2008</Year>
<Month>2</Month>
<Day>2</Day>
<Hour>9</Hour>
<Minute>0</Minute>
</PubMedPubDate>
</History>
<PublicationStatus>ppublish</PublicationStatus>
<ArticleIdList><ArticleId IdType="doi">10.1109/TNN.2003.811711</ArticleId>
<ArticleId IdType="pubmed">18238033</ArticleId>
</ArticleIdList>
</PubmedData>
</pubmed>
<affiliations><list><country><li>États-Unis</li>
</country>
<region><li>Nouveau-Mexique</li>
</region>
</list>
<tree><noCountry><name sortKey="Fugate, M" sort="Fugate, M" uniqKey="Fugate M" first="M" last="Fugate">M. Fugate</name>
<name sortKey="Hush, D R" sort="Hush, D R" uniqKey="Hush D" first="D R" last="Hush">D R Hush</name>
<name sortKey="Scovel, C" sort="Scovel, C" uniqKey="Scovel C" first="C" last="Scovel">C. Scovel</name>
</noCountry>
<country name="États-Unis"><region name="Nouveau-Mexique"><name sortKey="Cannon, M" sort="Cannon, M" uniqKey="Cannon M" first="M" last="Cannon">M. Cannon</name>
</region>
</country>
</tree>
</affiliations>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/PubMed/Checkpoint
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000066 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/PubMed/Checkpoint/biblio.hfd -nk 000066 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Ticri/CIDE |area= OcrV1 |flux= PubMed |étape= Checkpoint |type= RBID |clé= pubmed:18238033 |texte= Selecting a restoration technique to minimize OCR error. }}
Pour générer des pages wiki
HfdIndexSelect -h $EXPLOR_AREA/Data/PubMed/Checkpoint/RBID.i -Sk "pubmed:18238033" \ | HfdSelect -Kh $EXPLOR_AREA/Data/PubMed/Checkpoint/biblio.hfd \ | NlmPubMed2Wicri -a OcrV1
![]() | This area was generated with Dilib version V0.6.32. | ![]() |