A Document skew detection method using the hough transform
Identifieur interne : 001E55 ( Main/Exploration ); précédent : 001E54; suivant : 001E56A Document skew detection method using the hough transform
Auteurs : A. Amin [Australie] ; S. Fischer [Australie]Source :
- Pattern analysis and applications [ 1433-7541 ] ; 2000.
Descripteurs français
- Pascal (Inist)
- Scanneur, Reconnaissance caractère, Système optique, Reconnaissance forme, Traitement image, Interprétation image, Traitement document, Evaluation performance, Segmentation, Lecteur optique, Transformation Hough, Automatisation, Documentation, Texte, Méthode moindre carré, Projection, Profil, Reconnaissance optique caractère, Composante connexe.
- Wicri :
- topic : Automatisation, Documentation.
English descriptors
- KwdEn :
- Automation, Character recognition, Document processing, Documentation, Hough transformation, Image interpretation, Image processing, Least squares method, Optical character recognition, Optical reader, Optical system, Pattern recognition, Performance evaluation, Profile, Projection, Scanner, Segmentation, Text.
Abstract
Document image processing has become an increasingly important technology in the automation of office documentation tasks. Automatic document scanners such as text readers and OCR (Optical Character Recognition) systems are an essential component of systems capable of those tasks. One of the problems in this field is that the document to be read is not always placed correctly on a flatbed scanner. This means that the document may be skewed on the scanner bed, resulting in a skewed image. This skew has a detrimental effect on document analysis, document understanding, and character segmentation and recognition. Consequently, detecting the skew of a document image and correcting it are important issues in realising a practical document reader. In this paper we describe a new algorithm for skew detection. We then compare the performance and results of this skew detection algorithm to other published methods from O'Gorman, Hinds, Le, Baird, Postl and Akiyama. Finally, we discuss the theory of skew detection and the different approaches taken to solve the problem of skew in documents. The skew correction algorithm we propose has been shown to he extremely fast, with run times averaging under 0.25 CPU seconds to calculate the angle on a DEC 5000/20 workstation.
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream PascalFrancis, to step Corpus: 000763
- to stream PascalFrancis, to step Curation: 000031
- to stream PascalFrancis, to step Checkpoint: 000752
- to stream Main, to step Merge: 001F64
- to stream Main, to step Curation: 001E55
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">A Document skew detection method using the hough transform</title>
<author><name sortKey="Amin, A" sort="Amin, A" uniqKey="Amin A" first="A." last="Amin">A. Amin</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>School of Computer Science and Engineering, University of New South Wales</s1>
<s2>Sydney, NSW</s2>
<s3>AUS</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>Australie</country>
<wicri:noRegion>Sydney, NSW</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Fischer, S" sort="Fischer, S" uniqKey="Fischer S" first="S." last="Fischer">S. Fischer</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>School of Computer Science and Engineering, University of New South Wales</s1>
<s2>Sydney, NSW</s2>
<s3>AUS</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>Australie</country>
<wicri:noRegion>Sydney, NSW</wicri:noRegion>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">00-0489848</idno>
<date when="2000">2000</date>
<idno type="stanalyst">PASCAL 00-0489848 INIST</idno>
<idno type="RBID">Pascal:00-0489848</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000763</idno>
<idno type="wicri:Area/PascalFrancis/Curation">000031</idno>
<idno type="wicri:Area/PascalFrancis/Checkpoint">000752</idno>
<idno type="wicri:doubleKey">1433-7541:2000:Amin A:a:document:skew</idno>
<idno type="wicri:Area/Main/Merge">001F64</idno>
<idno type="wicri:Area/Main/Curation">001E55</idno>
<idno type="wicri:Area/Main/Exploration">001E55</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">A Document skew detection method using the hough transform</title>
<author><name sortKey="Amin, A" sort="Amin, A" uniqKey="Amin A" first="A." last="Amin">A. Amin</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>School of Computer Science and Engineering, University of New South Wales</s1>
<s2>Sydney, NSW</s2>
<s3>AUS</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>Australie</country>
<wicri:noRegion>Sydney, NSW</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Fischer, S" sort="Fischer, S" uniqKey="Fischer S" first="S." last="Fischer">S. Fischer</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>School of Computer Science and Engineering, University of New South Wales</s1>
<s2>Sydney, NSW</s2>
<s3>AUS</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>Australie</country>
<wicri:noRegion>Sydney, NSW</wicri:noRegion>
</affiliation>
</author>
</analytic>
<series><title level="j" type="main">Pattern analysis and applications</title>
<idno type="ISSN">1433-7541</idno>
<imprint><date when="2000">2000</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><title level="j" type="main">Pattern analysis and applications</title>
<idno type="ISSN">1433-7541</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Automation</term>
<term>Character recognition</term>
<term>Document processing</term>
<term>Documentation</term>
<term>Hough transformation</term>
<term>Image interpretation</term>
<term>Image processing</term>
<term>Least squares method</term>
<term>Optical character recognition</term>
<term>Optical reader</term>
<term>Optical system</term>
<term>Pattern recognition</term>
<term>Performance evaluation</term>
<term>Profile</term>
<term>Projection</term>
<term>Scanner</term>
<term>Segmentation</term>
<term>Text</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Scanneur</term>
<term>Reconnaissance caractère</term>
<term>Système optique</term>
<term>Reconnaissance forme</term>
<term>Traitement image</term>
<term>Interprétation image</term>
<term>Traitement document</term>
<term>Evaluation performance</term>
<term>Segmentation</term>
<term>Lecteur optique</term>
<term>Transformation Hough</term>
<term>Automatisation</term>
<term>Documentation</term>
<term>Texte</term>
<term>Méthode moindre carré</term>
<term>Projection</term>
<term>Profil</term>
<term>Reconnaissance optique caractère</term>
<term>Composante connexe</term>
</keywords>
<keywords scheme="Wicri" type="topic" xml:lang="fr"><term>Automatisation</term>
<term>Documentation</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">Document image processing has become an increasingly important technology in the automation of office documentation tasks. Automatic document scanners such as text readers and OCR (Optical Character Recognition) systems are an essential component of systems capable of those tasks. One of the problems in this field is that the document to be read is not always placed correctly on a flatbed scanner. This means that the document may be skewed on the scanner bed, resulting in a skewed image. This skew has a detrimental effect on document analysis, document understanding, and character segmentation and recognition. Consequently, detecting the skew of a document image and correcting it are important issues in realising a practical document reader. In this paper we describe a new algorithm for skew detection. We then compare the performance and results of this skew detection algorithm to other published methods from O'Gorman, Hinds, Le, Baird, Postl and Akiyama. Finally, we discuss the theory of skew detection and the different approaches taken to solve the problem of skew in documents. The skew correction algorithm we propose has been shown to he extremely fast, with run times averaging under 0.25 CPU seconds to calculate the angle on a DEC 5000/20 workstation.</div>
</front>
</TEI>
<affiliations><list><country><li>Australie</li>
</country>
</list>
<tree><country name="Australie"><noRegion><name sortKey="Amin, A" sort="Amin, A" uniqKey="Amin A" first="A." last="Amin">A. Amin</name>
</noRegion>
<name sortKey="Fischer, S" sort="Fischer, S" uniqKey="Fischer S" first="S." last="Fischer">S. Fischer</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 001E55 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 001E55 | 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= Pascal:00-0489848 |texte= A Document skew detection method using the hough transform }}
This area was generated with Dilib version V0.6.32. |