OcrV1, Main, Exploration, bibRecord, 001647

Automatic detection and recognition of signs from natural scenes

Identifieur interne : 001647 ( Main/Exploration ); précédent : 001646; suivant : 001648

Automatic detection and recognition of signs from natural scenes

Auteurs : XILIN CHEN [États-Unis] ; JIE YANG [États-Unis] ; JING ZHANG [États-Unis] ; Alex Waibel [États-Unis]

Source :

IEEE transactions on image processing [ 1057-7149 ] ; 2004.

RBID : Pascal:04-0171362

Descripteurs français

Pascal (Inist)
- Reconnaissance forme, Reconnaissance automatique, Reconnaissance caractère, Détection contour, Méthode échelle multiple, Analyse multirésolution, Extraction caractéristique, Analyse discriminante, Algorithme, Rectification affine.

English descriptors

KwdEn :
- Algorithm, Automatic recognition, Character recognition, Discriminant analysis, Edge detection, Feature extraction, Multiresolution analysis, Multiscale method, Pattern recognition.

Abstract

In this paper, we present an approach to automatic detection and recognition of signs from natural scenes, and its application to a sign translation task. The proposed approach embeds multiresolution and multiscale edge detection, adaptive searching, color analysis, and affine rectification in a hierarchical framework for sign detection, with different emphases at each phase to handle the text in different sizes, orientations, color distributions and backgrounds. We use affine rectification to recover deformation of the text regions caused by an inappropriate camera view angle. The procedure can significantly improve text detection rate and optical character recognition (OCR) accuracy. Instead of using binary information for OCR, we extract features from an intensity image directly. We propose a local intensity normalization method to effectively handle lighting variations, followed by a Gabor transform to obtain local features, and finally a linear discriminant analysis (LDA) method for feature selection. We have applied the approach in developing a Chinese sign translation system, which can automatically detect and recognize Chinese signs as input from a camera, and translate the recognized text into English.

Affiliations:

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

to stream PascalFrancis, to step Corpus: 000560
to stream PascalFrancis, to step Curation: 000230
to stream PascalFrancis, to step Checkpoint: 000502
to stream Main, to step Merge: 001713
to stream Main, to step Curation: 001647

Le document en format XML

<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Automatic detection and recognition of signs from natural scenes</title>
<author><name sortKey="Xilin Chen" sort="Xilin Chen" uniqKey="Xilin Chen" last="Xilin Chen">XILIN CHEN</name>
<affiliation wicri:level="4"><inist:fA14 i1="01"><s1>School of Computer Science, Carnegie Mellon University</s1>
<s2>Pittsburgh, PA, 15213</s2>
<s3>USA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>4 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
<placeName><settlement type="city">Pittsburgh</settlement>
<region type="state">Pennsylvanie</region>
</placeName>
<orgName type="university">Université Carnegie-Mellon</orgName>
</affiliation>
</author>
<author><name sortKey="Jie Yang" sort="Jie Yang" uniqKey="Jie Yang" last="Jie Yang">JIE YANG</name>
<affiliation wicri:level="4"><inist:fA14 i1="01"><s1>School of Computer Science, Carnegie Mellon University</s1>
<s2>Pittsburgh, PA, 15213</s2>
<s3>USA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>4 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
<placeName><settlement type="city">Pittsburgh</settlement>
<region type="state">Pennsylvanie</region>
</placeName>
<orgName type="university">Université Carnegie-Mellon</orgName>
</affiliation>
</author>
<author><name sortKey="Jing Zhang" sort="Jing Zhang" uniqKey="Jing Zhang" last="Jing Zhang">JING ZHANG</name>
<affiliation wicri:level="1"><inist:fA14 i1="02"><s1>Mobile Technologies, LLC</s1>
<s2>Pittsburgh, PA, 15213</s2>
<s3>USA</s3>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
<wicri:noRegion>Pittsburgh, PA, 15213</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Waibel, Alex" sort="Waibel, Alex" uniqKey="Waibel A" first="Alex" last="Waibel">Alex Waibel</name>
<affiliation wicri:level="4"><inist:fA14 i1="01"><s1>School of Computer Science, Carnegie Mellon University</s1>
<s2>Pittsburgh, PA, 15213</s2>
<s3>USA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>4 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
<placeName><settlement type="city">Pittsburgh</settlement>
<region type="state">Pennsylvanie</region>
</placeName>
<orgName type="university">Université Carnegie-Mellon</orgName>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">04-0171362</idno>
<date when="2004">2004</date>
<idno type="stanalyst">PASCAL 04-0171362 INIST</idno>
<idno type="RBID">Pascal:04-0171362</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000560</idno>
<idno type="wicri:Area/PascalFrancis/Curation">000230</idno>
<idno type="wicri:Area/PascalFrancis/Checkpoint">000502</idno>
<idno type="wicri:doubleKey">1057-7149:2004:Xilin Chen:automatic:detection:and</idno>
<idno type="wicri:Area/Main/Merge">001713</idno>
<idno type="wicri:Area/Main/Curation">001647</idno>
<idno type="wicri:Area/Main/Exploration">001647</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Automatic detection and recognition of signs from natural scenes</title>
<author><name sortKey="Xilin Chen" sort="Xilin Chen" uniqKey="Xilin Chen" last="Xilin Chen">XILIN CHEN</name>
<affiliation wicri:level="4"><inist:fA14 i1="01"><s1>School of Computer Science, Carnegie Mellon University</s1>
<s2>Pittsburgh, PA, 15213</s2>
<s3>USA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>4 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
<placeName><settlement type="city">Pittsburgh</settlement>
<region type="state">Pennsylvanie</region>
</placeName>
<orgName type="university">Université Carnegie-Mellon</orgName>
</affiliation>
</author>
<author><name sortKey="Jie Yang" sort="Jie Yang" uniqKey="Jie Yang" last="Jie Yang">JIE YANG</name>
<affiliation wicri:level="4"><inist:fA14 i1="01"><s1>School of Computer Science, Carnegie Mellon University</s1>
<s2>Pittsburgh, PA, 15213</s2>
<s3>USA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>4 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
<placeName><settlement type="city">Pittsburgh</settlement>
<region type="state">Pennsylvanie</region>
</placeName>
<orgName type="university">Université Carnegie-Mellon</orgName>
</affiliation>
</author>
<author><name sortKey="Jing Zhang" sort="Jing Zhang" uniqKey="Jing Zhang" last="Jing Zhang">JING ZHANG</name>
<affiliation wicri:level="1"><inist:fA14 i1="02"><s1>Mobile Technologies, LLC</s1>
<s2>Pittsburgh, PA, 15213</s2>
<s3>USA</s3>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
<wicri:noRegion>Pittsburgh, PA, 15213</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Waibel, Alex" sort="Waibel, Alex" uniqKey="Waibel A" first="Alex" last="Waibel">Alex Waibel</name>
<affiliation wicri:level="4"><inist:fA14 i1="01"><s1>School of Computer Science, Carnegie Mellon University</s1>
<s2>Pittsburgh, PA, 15213</s2>
<s3>USA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>4 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
<placeName><settlement type="city">Pittsburgh</settlement>
<region type="state">Pennsylvanie</region>
</placeName>
<orgName type="university">Université Carnegie-Mellon</orgName>
</affiliation>
</author>
</analytic>
<series><title level="j" type="main">IEEE transactions on image processing</title>
<title level="j" type="abbreviated">IEEE trans. image process.</title>
<idno type="ISSN">1057-7149</idno>
<imprint><date when="2004">2004</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><title level="j" type="main">IEEE transactions on image processing</title>
<title level="j" type="abbreviated">IEEE trans. image process.</title>
<idno type="ISSN">1057-7149</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Algorithm</term>
<term>Automatic recognition</term>
<term>Character recognition</term>
<term>Discriminant analysis</term>
<term>Edge detection</term>
<term>Feature extraction</term>
<term>Multiresolution analysis</term>
<term>Multiscale method</term>
<term>Pattern recognition</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Reconnaissance forme</term>
<term>Reconnaissance automatique</term>
<term>Reconnaissance caractère</term>
<term>Détection contour</term>
<term>Méthode échelle multiple</term>
<term>Analyse multirésolution</term>
<term>Extraction caractéristique</term>
<term>Analyse discriminante</term>
<term>Algorithme</term>
<term>Rectification affine</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">In this paper, we present an approach to automatic detection and recognition of signs from natural scenes, and its application to a sign translation task. The proposed approach embeds multiresolution and multiscale edge detection, adaptive searching, color analysis, and affine rectification in a hierarchical framework for sign detection, with different emphases at each phase to handle the text in different sizes, orientations, color distributions and backgrounds. We use affine rectification to recover deformation of the text regions caused by an inappropriate camera view angle. The procedure can significantly improve text detection rate and optical character recognition (OCR) accuracy. Instead of using binary information for OCR, we extract features from an intensity image directly. We propose a local intensity normalization method to effectively handle lighting variations, followed by a Gabor transform to obtain local features, and finally a linear discriminant analysis (LDA) method for feature selection. We have applied the approach in developing a Chinese sign translation system, which can automatically detect and recognize Chinese signs as input from a camera, and translate the recognized text into English.</div>
</front>
</TEI>
<affiliations><list><country><li>États-Unis</li>
</country>
<region><li>Pennsylvanie</li>
</region>
<settlement><li>Pittsburgh</li>
</settlement>
<orgName><li>Université Carnegie-Mellon</li>
</orgName>
</list>
<tree><country name="États-Unis"><region name="Pennsylvanie"><name sortKey="Xilin Chen" sort="Xilin Chen" uniqKey="Xilin Chen" last="Xilin Chen">XILIN CHEN</name>
</region>
<name sortKey="Jie Yang" sort="Jie Yang" uniqKey="Jie Yang" last="Jie Yang">JIE YANG</name>
<name sortKey="Jing Zhang" sort="Jing Zhang" uniqKey="Jing Zhang" last="Jing Zhang">JING ZHANG</name>
<name sortKey="Waibel, Alex" sort="Waibel, Alex" uniqKey="Waibel A" first="Alex" last="Waibel">Alex Waibel</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 001647 | SxmlIndent | more

HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 001647 | 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:04-0171362
   |texte=   Automatic detection and recognition of signs from natural scenes
}}

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

Automatic detection and recognition of signs from natural scenes

Automatic detection and recognition of signs from natural scenes

Source :

Descripteurs français

English descriptors

Abstract

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

Le document en format XML

Pour manipuler ce document sous Unix (Dilib)

Pour mettre un lien sur cette page dans le réseau Wicri