OcrV1, France, Analysis, bibRecord, 000215

A novel approach for text detection in images using structural features

Identifieur interne : 000215 ( France/Analysis ); précédent : 000214; suivant : 000216

A novel approach for text detection in images using structural features

Auteurs : H. Trai [France, Viêt Nam] ; A. Lux [France] ; H. L. Nguyen T [Viêt Nam] ; A. Boucher [France]

Source :

Lecture notes in computer science [ 0302-9743 ] ; 2005.

RBID : Pascal:05-0391618

Descripteurs français

Pascal (Inist)
- Fouille donnée, Reconnaissance forme, Texte, Détecteur image, Analyse image, Chaîne caractère, Squelette, Parallélisme, Reconnaissance caractère, Reconnaissance optique caractère, Analyse texte.

English descriptors

KwdEn :
- Character recognition, Character string, Data mining, Image analysis, Image sensor, Optical character recognition, Parallelism, Pattern recognition, Skeleton, Text, Text analysis.

Abstract

We propose a novel approach for finding text in images by using ridges at several scales. A text string is modelled by a ridge at a coarse scale representing its center line and numerous short ridges at a smaller scale representing the skeletons of characters. Skeleton ridges have to satisfy geometrical and spatial constraints such as the perpendicularity or non-parallelism to the central ridge. In this way, we obtain a hierarchical description of text strings, which can provide direct input to an OCR or a text analysis system. The proposed method does not depend on a particular alphabet, it works with a wide variety in size of characters and does not depend on orientation of text string. The experimental results show a good detection.

Affiliations:

France, Viêt Nam

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

to stream PascalFrancis, to step Corpus: 000450
to stream PascalFrancis, to step Curation: 000338
to stream PascalFrancis, to step Checkpoint: 000440
to stream Main, to step Merge: 001470
to stream Main, to step Curation: 001422
to stream Main, to step Exploration: 001422
to stream France, to step Extraction: 000215

Links to Exploration step

Pascal:05-0391618

Le document en format XML

<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">A novel approach for text detection in images using structural features</title>
<author><name sortKey="Trai, H" sort="Trai, H" uniqKey="Trai H" first="H." last="Trai">H. Trai</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Institut National Polytechnique de Grenoble, Laboratory GRAVIR, INRIA</s1>
<s2>Rhone-Alpes</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>France</country>
<wicri:noRegion>Rhone-Alpes</wicri:noRegion>
<wicri:noRegion>INRIA</wicri:noRegion>
<wicri:noRegion>Rhone-Alpes</wicri:noRegion>
</affiliation>
<affiliation wicri:level="1"><inist:fA14 i1="02"><s1>Hanoi University of Technology, International Research Center MICA</s1>
<s2>Hanoi</s2>
<s3>VNM</s3>
<sZ>1 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>Viêt Nam</country>
<wicri:noRegion>Hanoi</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Lux, A" sort="Lux, A" uniqKey="Lux A" first="A." last="Lux">A. Lux</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Institut National Polytechnique de Grenoble, Laboratory GRAVIR, INRIA</s1>
<s2>Rhone-Alpes</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>France</country>
<wicri:noRegion>Rhone-Alpes</wicri:noRegion>
<wicri:noRegion>INRIA</wicri:noRegion>
<wicri:noRegion>Rhone-Alpes</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Nguyen T, H L" sort="Nguyen T, H L" uniqKey="Nguyen T H" first="H. L." last="Nguyen T">H. L. Nguyen T</name>
<affiliation wicri:level="1"><inist:fA14 i1="02"><s1>Hanoi University of Technology, International Research Center MICA</s1>
<s2>Hanoi</s2>
<s3>VNM</s3>
<sZ>1 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>Viêt Nam</country>
<wicri:noRegion>Hanoi</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Boucher, A" sort="Boucher, A" uniqKey="Boucher A" first="A." last="Boucher">A. Boucher</name>
<affiliation wicri:level="1"><inist:fA14 i1="03"><s1>Institut de la Francophonie pour l'Informatique</s1>
<s3>FRA</s3>
<sZ>4 aut.</sZ>
</inist:fA14>
<country>France</country>
<wicri:noRegion>Institut de la Francophonie pour l'Informatique</wicri:noRegion>
<wicri:noRegion>Institut de la Francophonie pour l'Informatique</wicri:noRegion>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">05-0391618</idno>
<date when="2005">2005</date>
<idno type="stanalyst">PASCAL 05-0391618 INIST</idno>
<idno type="RBID">Pascal:05-0391618</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000450</idno>
<idno type="wicri:Area/PascalFrancis/Curation">000338</idno>
<idno type="wicri:Area/PascalFrancis/Checkpoint">000440</idno>
<idno type="wicri:doubleKey">0302-9743:2005:Trai H:a:novel:approach</idno>
<idno type="wicri:Area/Main/Merge">001470</idno>
<idno type="wicri:Area/Main/Curation">001422</idno>
<idno type="wicri:Area/Main/Exploration">001422</idno>
<idno type="wicri:Area/France/Extraction">000215</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">A novel approach for text detection in images using structural features</title>
<author><name sortKey="Trai, H" sort="Trai, H" uniqKey="Trai H" first="H." last="Trai">H. Trai</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Institut National Polytechnique de Grenoble, Laboratory GRAVIR, INRIA</s1>
<s2>Rhone-Alpes</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>France</country>
<wicri:noRegion>Rhone-Alpes</wicri:noRegion>
<wicri:noRegion>INRIA</wicri:noRegion>
<wicri:noRegion>Rhone-Alpes</wicri:noRegion>
</affiliation>
<affiliation wicri:level="1"><inist:fA14 i1="02"><s1>Hanoi University of Technology, International Research Center MICA</s1>
<s2>Hanoi</s2>
<s3>VNM</s3>
<sZ>1 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>Viêt Nam</country>
<wicri:noRegion>Hanoi</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Lux, A" sort="Lux, A" uniqKey="Lux A" first="A." last="Lux">A. Lux</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Institut National Polytechnique de Grenoble, Laboratory GRAVIR, INRIA</s1>
<s2>Rhone-Alpes</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>France</country>
<wicri:noRegion>Rhone-Alpes</wicri:noRegion>
<wicri:noRegion>INRIA</wicri:noRegion>
<wicri:noRegion>Rhone-Alpes</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Nguyen T, H L" sort="Nguyen T, H L" uniqKey="Nguyen T H" first="H. L." last="Nguyen T">H. L. Nguyen T</name>
<affiliation wicri:level="1"><inist:fA14 i1="02"><s1>Hanoi University of Technology, International Research Center MICA</s1>
<s2>Hanoi</s2>
<s3>VNM</s3>
<sZ>1 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>Viêt Nam</country>
<wicri:noRegion>Hanoi</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Boucher, A" sort="Boucher, A" uniqKey="Boucher A" first="A." last="Boucher">A. Boucher</name>
<affiliation wicri:level="1"><inist:fA14 i1="03"><s1>Institut de la Francophonie pour l'Informatique</s1>
<s3>FRA</s3>
<sZ>4 aut.</sZ>
</inist:fA14>
<country>France</country>
<wicri:noRegion>Institut de la Francophonie pour l'Informatique</wicri:noRegion>
<wicri:noRegion>Institut de la Francophonie pour l'Informatique</wicri:noRegion>
</affiliation>
</author>
</analytic>
<series><title level="j" type="main">Lecture notes in computer science</title>
<idno type="ISSN">0302-9743</idno>
<imprint><date when="2005">2005</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>Character string</term>
<term>Data mining</term>
<term>Image analysis</term>
<term>Image sensor</term>
<term>Optical character recognition</term>
<term>Parallelism</term>
<term>Pattern recognition</term>
<term>Skeleton</term>
<term>Text</term>
<term>Text analysis</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Fouille donnée</term>
<term>Reconnaissance forme</term>
<term>Texte</term>
<term>Détecteur image</term>
<term>Analyse image</term>
<term>Chaîne caractère</term>
<term>Squelette</term>
<term>Parallélisme</term>
<term>Reconnaissance caractère</term>
<term>Reconnaissance optique caractère</term>
<term>Analyse texte</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">We propose a novel approach for finding text in images by using ridges at several scales. A text string is modelled by a ridge at a coarse scale representing its center line and numerous short ridges at a smaller scale representing the skeletons of characters. Skeleton ridges have to satisfy geometrical and spatial constraints such as the perpendicularity or non-parallelism to the central ridge. In this way, we obtain a hierarchical description of text strings, which can provide direct input to an OCR or a text analysis system. The proposed method does not depend on a particular alphabet, it works with a wide variety in size of characters and does not depend on orientation of text string. The experimental results show a good detection.</div>
</front>
</TEI>
<affiliations><list><country><li>France</li>
<li>Viêt Nam</li>
</country>
</list>
<tree><country name="France"><noRegion><name sortKey="Trai, H" sort="Trai, H" uniqKey="Trai H" first="H." last="Trai">H. Trai</name>
</noRegion>
<name sortKey="Boucher, A" sort="Boucher, A" uniqKey="Boucher A" first="A." last="Boucher">A. Boucher</name>
<name sortKey="Lux, A" sort="Lux, A" uniqKey="Lux A" first="A." last="Lux">A. Lux</name>
</country>
<country name="Viêt Nam"><noRegion><name sortKey="Trai, H" sort="Trai, H" uniqKey="Trai H" first="H." last="Trai">H. Trai</name>
</noRegion>
<name sortKey="Nguyen T, H L" sort="Nguyen T, H L" uniqKey="Nguyen T H" first="H. L." last="Nguyen T">H. L. Nguyen T</name>
</country>
</tree>
</affiliations>
</record>

Pour manipuler ce document sous Unix (Dilib)

EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/France/Analysis

HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000215 | SxmlIndent | more

HfdSelect -h $EXPLOR_AREA/Data/France/Analysis/biblio.hfd -nk 000215 | SxmlIndent | more

Pour mettre un lien sur cette page dans le réseau Wicri

{{Explor lien
   |wiki=    Ticri/CIDE
   |area=    OcrV1
   |flux=    France
   |étape=   Analysis
   |type=    RBID
   |clé=     Pascal:05-0391618
   |texte=   A novel approach for text detection in images using structural features
}}

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

A novel approach for text detection in images using structural features

A novel approach for text detection in images using structural features

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