OcrV1, Main, Merge, bibRecord, 001166

The effects of OCR error on the extraction of private information

Identifieur interne : 001166 ( Main/Merge ); précédent : 001165; suivant : 001167

The effects of OCR error on the extraction of private information

Auteurs : Kazem Taghva [États-Unis] ; Russell Beckley [États-Unis] ; Jeffrey Coombs [États-Unis]

Source :

Lecture notes in computer science [ 0302-9743 ] ; 2006.

RBID : Pascal:08-0029057

Descripteurs français

Pascal (Inist)
- Traitement image, Reconnaissance forme, Analyse documentaire, Structure document, Reconnaissance caractère, Reconnaissance optique caractère, Extraction information, Vie privée, Linguistique, Texte, Classification.
Wicri :
- topic : Linguistique, Classification.

English descriptors

KwdEn :
- Character recognition, Classification, Document analysis, Document structure, Image processing, Information extraction, Linguistics, Optical character recognition, Pattern recognition, Private life, Text.

Abstract

OCR error has been shown not to affect the average accuracy of text retrieval or text categorization. Recent studies however have indicated that information extraction is significantly degraded by OCR error. We experimented with information extraction software on two collections, one with OCR-ed documents and another with manually-corrected versions of the former. We discovered a significant reduction in accuracy on the OCR text versus the corrected text. The majority of errors were attributable to zoning problems rather than OCR classification errors.

Links toward previous steps (curation, corpus...)

to stream PascalFrancis, to step Corpus: 000301
to stream PascalFrancis, to step Curation: 000483
to stream PascalFrancis, to step Checkpoint: 000305

Links to Exploration step

Pascal:08-0029057

Le document en format XML

<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">The effects of OCR error on the extraction of private information</title>
<author><name sortKey="Taghva, Kazem" sort="Taghva, Kazem" uniqKey="Taghva K" first="Kazem" last="Taghva">Kazem Taghva</name>
<affiliation wicri:level="3"><inist:fA14 i1="01"><s1>Information Science Research Institute, University of Nevada</s1>
<s2>Las Vegas</s2>
<s3>USA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
<placeName><settlement type="city">Las Vegas</settlement>
<region type="state">Nevada</region>
</placeName>
</affiliation>
</author>
<author><name sortKey="Beckley, Russell" sort="Beckley, Russell" uniqKey="Beckley R" first="Russell" last="Beckley">Russell Beckley</name>
<affiliation wicri:level="3"><inist:fA14 i1="01"><s1>Information Science Research Institute, University of Nevada</s1>
<s2>Las Vegas</s2>
<s3>USA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
<placeName><settlement type="city">Las Vegas</settlement>
<region type="state">Nevada</region>
</placeName>
</affiliation>
</author>
<author><name sortKey="Coombs, Jeffrey" sort="Coombs, Jeffrey" uniqKey="Coombs J" first="Jeffrey" last="Coombs">Jeffrey Coombs</name>
<affiliation wicri:level="3"><inist:fA14 i1="01"><s1>Information Science Research Institute, University of Nevada</s1>
<s2>Las Vegas</s2>
<s3>USA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
<placeName><settlement type="city">Las Vegas</settlement>
<region type="state">Nevada</region>
</placeName>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">08-0029057</idno>
<date when="2006">2006</date>
<idno type="stanalyst">PASCAL 08-0029057 INIST</idno>
<idno type="RBID">Pascal:08-0029057</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000301</idno>
<idno type="wicri:Area/PascalFrancis/Curation">000483</idno>
<idno type="wicri:Area/PascalFrancis/Checkpoint">000305</idno>
<idno type="wicri:doubleKey">0302-9743:2006:Taghva K:the:effects:of</idno>
<idno type="wicri:Area/Main/Merge">001166</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">The effects of OCR error on the extraction of private information</title>
<author><name sortKey="Taghva, Kazem" sort="Taghva, Kazem" uniqKey="Taghva K" first="Kazem" last="Taghva">Kazem Taghva</name>
<affiliation wicri:level="3"><inist:fA14 i1="01"><s1>Information Science Research Institute, University of Nevada</s1>
<s2>Las Vegas</s2>
<s3>USA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
<placeName><settlement type="city">Las Vegas</settlement>
<region type="state">Nevada</region>
</placeName>
</affiliation>
</author>
<author><name sortKey="Beckley, Russell" sort="Beckley, Russell" uniqKey="Beckley R" first="Russell" last="Beckley">Russell Beckley</name>
<affiliation wicri:level="3"><inist:fA14 i1="01"><s1>Information Science Research Institute, University of Nevada</s1>
<s2>Las Vegas</s2>
<s3>USA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
<placeName><settlement type="city">Las Vegas</settlement>
<region type="state">Nevada</region>
</placeName>
</affiliation>
</author>
<author><name sortKey="Coombs, Jeffrey" sort="Coombs, Jeffrey" uniqKey="Coombs J" first="Jeffrey" last="Coombs">Jeffrey Coombs</name>
<affiliation wicri:level="3"><inist:fA14 i1="01"><s1>Information Science Research Institute, University of Nevada</s1>
<s2>Las Vegas</s2>
<s3>USA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
<placeName><settlement type="city">Las Vegas</settlement>
<region type="state">Nevada</region>
</placeName>
</affiliation>
</author>
</analytic>
<series><title level="j" type="main">Lecture notes in computer science</title>
<idno type="ISSN">0302-9743</idno>
<imprint><date when="2006">2006</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><title level="j" type="main">Lecture notes in computer science</title>
<idno type="ISSN">0302-9743</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Character recognition</term>
<term>Classification</term>
<term>Document analysis</term>
<term>Document structure</term>
<term>Image processing</term>
<term>Information extraction</term>
<term>Linguistics</term>
<term>Optical character recognition</term>
<term>Pattern recognition</term>
<term>Private life</term>
<term>Text</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Traitement image</term>
<term>Reconnaissance forme</term>
<term>Analyse documentaire</term>
<term>Structure document</term>
<term>Reconnaissance caractère</term>
<term>Reconnaissance optique caractère</term>
<term>Extraction information</term>
<term>Vie privée</term>
<term>Linguistique</term>
<term>Texte</term>
<term>Classification</term>
</keywords>
<keywords scheme="Wicri" type="topic" xml:lang="fr"><term>Linguistique</term>
<term>Classification</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">OCR error has been shown not to affect the average accuracy of text retrieval or text categorization. Recent studies however have indicated that information extraction is significantly degraded by OCR error. We experimented with information extraction software on two collections, one with OCR-ed documents and another with manually-corrected versions of the former. We discovered a significant reduction in accuracy on the OCR text versus the corrected text. The majority of errors were attributable to zoning problems rather than OCR classification errors.</div>
</front>
</TEI>
<affiliations><list><country><li>États-Unis</li>
</country>
<region><li>Nevada</li>
</region>
<settlement><li>Las Vegas</li>
</settlement>
</list>
<tree><country name="États-Unis"><region name="Nevada"><name sortKey="Taghva, Kazem" sort="Taghva, Kazem" uniqKey="Taghva K" first="Kazem" last="Taghva">Kazem Taghva</name>
</region>
<name sortKey="Beckley, Russell" sort="Beckley, Russell" uniqKey="Beckley R" first="Russell" last="Beckley">Russell Beckley</name>
<name sortKey="Coombs, Jeffrey" sort="Coombs, Jeffrey" uniqKey="Coombs J" first="Jeffrey" last="Coombs">Jeffrey Coombs</name>
</country>
</tree>
</affiliations>
</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 001166 | SxmlIndent | more

HfdSelect -h $EXPLOR_AREA/Data/Main/Merge/biblio.hfd -nk 001166 | 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=     Pascal:08-0029057
   |texte=   The effects of OCR error on the extraction of private information
}}

This area was generated with Dilib version V0.6.32.
Data generation: Sat Nov 11 16:53:45 2017. Site generation: Mon Mar 11 23:15:16 2024

	Serveur d'exploration sur l'OCR
	Attention, ce site est en cours de développement ! Attention, site généré par des moyens informatiques à partir de corpus bruts. Les informations ne sont donc pas validées.

Serveur d'exploration sur l'OCR

The effects of OCR error on the extraction of private information

The effects of OCR error on the extraction of private information

Source :

Descripteurs français

English descriptors

Abstract

Links toward previous steps (curation, corpus...)

Links to Exploration step

Le document en format XML

Pour manipuler ce document sous Unix (Dilib)

Pour mettre un lien sur cette page dans le réseau Wicri