Automatic detection and recognition of signs from natural scenes.
Identifieur interne : 000065 ( PubMed/Checkpoint ); précédent : 000064; suivant : 000066Automatic detection and recognition of signs from natural scenes.
Auteurs : Xilin Chen [États-Unis] ; Jie Yang ; Jing Zhang ; Alex WaibelSource :
- IEEE transactions on image processing : a publication of the IEEE Signal Processing Society [ 1057-7149 ] ; 2004.
English descriptors
- KwdEn :
- Algorithms, Automatic Data Processing (methods), Image Enhancement (methods), Image Interpretation, Computer-Assisted (methods), Information Storage and Retrieval (methods), Location Directories and Signs, Pattern Recognition, Automated, Reproducibility of Results, Robotics (methods), Sensitivity and Specificity, Signal Processing, Computer-Assisted.
- MESH :
- methods : Automatic Data Processing, Image Enhancement, Image Interpretation, Computer-Assisted, Information Storage and Retrieval, Robotics.
- Algorithms, Location Directories and Signs, Pattern Recognition, Automated, Reproducibility of Results, Sensitivity and Specificity, Signal Processing, Computer-Assisted.
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.
PubMed: 15376960
Affiliations:
Links toward previous steps (curation, corpus...)
Links to Exploration step
pubmed:15376960Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">Automatic detection and recognition of signs from natural scenes.</title>
<author><name sortKey="Chen, Xilin" sort="Chen, Xilin" uniqKey="Chen X" first="Xilin" last="Chen">Xilin Chen</name>
<affiliation wicri:level="4"><nlm:affiliation>School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, 15213 USA. xlchen@cs.cmu.edu</nlm:affiliation>
<country xml:lang="fr">États-Unis</country>
<wicri:regionArea>School of Computer Science, Carnegie Mellon University, Pittsburgh, PA</wicri:regionArea>
<placeName><region type="state">Pennsylvanie</region>
<settlement type="city">Pittsburgh</settlement>
</placeName>
<orgName type="university">Université Carnegie-Mellon</orgName>
</affiliation>
</author>
<author><name sortKey="Yang, Jie" sort="Yang, Jie" uniqKey="Yang J" first="Jie" last="Yang">Jie Yang</name>
</author>
<author><name sortKey="Zhang, Jing" sort="Zhang, Jing" uniqKey="Zhang J" first="Jing" last="Zhang">Jing Zhang</name>
</author>
<author><name sortKey="Waibel, Alex" sort="Waibel, Alex" uniqKey="Waibel A" first="Alex" last="Waibel">Alex Waibel</name>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">PubMed</idno>
<date when="2004">2004</date>
<idno type="RBID">pubmed:15376960</idno>
<idno type="pmid">15376960</idno>
<idno type="wicri:Area/PubMed/Corpus">000071</idno>
<idno type="wicri:Area/PubMed/Curation">000071</idno>
<idno type="wicri:Area/PubMed/Checkpoint">000071</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en">Automatic detection and recognition of signs from natural scenes.</title>
<author><name sortKey="Chen, Xilin" sort="Chen, Xilin" uniqKey="Chen X" first="Xilin" last="Chen">Xilin Chen</name>
<affiliation wicri:level="4"><nlm:affiliation>School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, 15213 USA. xlchen@cs.cmu.edu</nlm:affiliation>
<country xml:lang="fr">États-Unis</country>
<wicri:regionArea>School of Computer Science, Carnegie Mellon University, Pittsburgh, PA</wicri:regionArea>
<placeName><region type="state">Pennsylvanie</region>
<settlement type="city">Pittsburgh</settlement>
</placeName>
<orgName type="university">Université Carnegie-Mellon</orgName>
</affiliation>
</author>
<author><name sortKey="Yang, Jie" sort="Yang, Jie" uniqKey="Yang J" first="Jie" last="Yang">Jie Yang</name>
</author>
<author><name sortKey="Zhang, Jing" sort="Zhang, Jing" uniqKey="Zhang J" first="Jing" last="Zhang">Jing Zhang</name>
</author>
<author><name sortKey="Waibel, Alex" sort="Waibel, Alex" uniqKey="Waibel A" first="Alex" last="Waibel">Alex Waibel</name>
</author>
</analytic>
<series><title level="j">IEEE transactions on image processing : a publication of the IEEE Signal Processing Society</title>
<idno type="ISSN">1057-7149</idno>
<imprint><date when="2004" type="published">2004</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Algorithms</term>
<term>Automatic Data Processing (methods)</term>
<term>Image Enhancement (methods)</term>
<term>Image Interpretation, Computer-Assisted (methods)</term>
<term>Information Storage and Retrieval (methods)</term>
<term>Location Directories and Signs</term>
<term>Pattern Recognition, Automated</term>
<term>Reproducibility of Results</term>
<term>Robotics (methods)</term>
<term>Sensitivity and Specificity</term>
<term>Signal Processing, Computer-Assisted</term>
</keywords>
<keywords scheme="MESH" qualifier="methods" xml:lang="en"><term>Automatic Data Processing</term>
<term>Image Enhancement</term>
<term>Image Interpretation, Computer-Assisted</term>
<term>Information Storage and Retrieval</term>
<term>Robotics</term>
</keywords>
<keywords scheme="MESH" xml:lang="en"><term>Algorithms</term>
<term>Location Directories and Signs</term>
<term>Pattern Recognition, Automated</term>
<term>Reproducibility of Results</term>
<term>Sensitivity and Specificity</term>
<term>Signal Processing, Computer-Assisted</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>
<pubmed><MedlineCitation Owner="NLM" Status="MEDLINE"><PMID Version="1">15376960</PMID>
<DateCreated><Year>2004</Year>
<Month>09</Month>
<Day>20</Day>
</DateCreated>
<DateCompleted><Year>2004</Year>
<Month>10</Month>
<Day>12</Day>
</DateCompleted>
<DateRevised><Year>2006</Year>
<Month>11</Month>
<Day>15</Day>
</DateRevised>
<Article PubModel="Print"><Journal><ISSN IssnType="Print">1057-7149</ISSN>
<JournalIssue CitedMedium="Print"><Volume>13</Volume>
<Issue>1</Issue>
<PubDate><Year>2004</Year>
<Month>Jan</Month>
</PubDate>
</JournalIssue>
<Title>IEEE transactions on image processing : a publication of the IEEE Signal Processing Society</Title>
<ISOAbbreviation>IEEE Trans Image Process</ISOAbbreviation>
</Journal>
<ArticleTitle>Automatic detection and recognition of signs from natural scenes.</ArticleTitle>
<Pagination><MedlinePgn>87-99</MedlinePgn>
</Pagination>
<Abstract><AbstractText>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.</AbstractText>
</Abstract>
<AuthorList CompleteYN="Y"><Author ValidYN="Y"><LastName>Chen</LastName>
<ForeName>Xilin</ForeName>
<Initials>X</Initials>
<AffiliationInfo><Affiliation>School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, 15213 USA. xlchen@cs.cmu.edu</Affiliation>
</AffiliationInfo>
</Author>
<Author ValidYN="Y"><LastName>Yang</LastName>
<ForeName>Jie</ForeName>
<Initials>J</Initials>
</Author>
<Author ValidYN="Y"><LastName>Zhang</LastName>
<ForeName>Jing</ForeName>
<Initials>J</Initials>
</Author>
<Author ValidYN="Y"><LastName>Waibel</LastName>
<ForeName>Alex</ForeName>
<Initials>A</Initials>
</Author>
</AuthorList>
<Language>eng</Language>
<PublicationTypeList><PublicationType UI="D003160">Comparative Study</PublicationType>
<PublicationType UI="D023362">Evaluation Studies</PublicationType>
<PublicationType UI="D016428">Journal Article</PublicationType>
<PublicationType UI="D013486">Research Support, U.S. Gov't, Non-P.H.S.</PublicationType>
<PublicationType UI="D023361">Validation Studies</PublicationType>
</PublicationTypeList>
</Article>
<MedlineJournalInfo><Country>United States</Country>
<MedlineTA>IEEE Trans Image Process</MedlineTA>
<NlmUniqueID>9886191</NlmUniqueID>
<ISSNLinking>1057-7149</ISSNLinking>
</MedlineJournalInfo>
<CitationSubset>IM</CitationSubset>
<MeshHeadingList><MeshHeading><DescriptorName MajorTopicYN="Y" UI="D000465">Algorithms</DescriptorName>
</MeshHeading>
<MeshHeading><DescriptorName MajorTopicYN="N" UI="D001330">Automatic Data Processing</DescriptorName>
<QualifierName MajorTopicYN="Y" UI="Q000379">methods</QualifierName>
</MeshHeading>
<MeshHeading><DescriptorName MajorTopicYN="N" UI="D007089">Image Enhancement</DescriptorName>
<QualifierName MajorTopicYN="Y" UI="Q000379">methods</QualifierName>
</MeshHeading>
<MeshHeading><DescriptorName MajorTopicYN="N" UI="D007090">Image Interpretation, Computer-Assisted</DescriptorName>
<QualifierName MajorTopicYN="Y" UI="Q000379">methods</QualifierName>
</MeshHeading>
<MeshHeading><DescriptorName MajorTopicYN="N" UI="D016247">Information Storage and Retrieval</DescriptorName>
<QualifierName MajorTopicYN="Y" UI="Q000379">methods</QualifierName>
</MeshHeading>
<MeshHeading><DescriptorName MajorTopicYN="Y" UI="D008123">Location Directories and Signs</DescriptorName>
</MeshHeading>
<MeshHeading><DescriptorName MajorTopicYN="Y" UI="D010363">Pattern Recognition, Automated</DescriptorName>
</MeshHeading>
<MeshHeading><DescriptorName MajorTopicYN="N" UI="D015203">Reproducibility of Results</DescriptorName>
</MeshHeading>
<MeshHeading><DescriptorName MajorTopicYN="N" UI="D012371">Robotics</DescriptorName>
<QualifierName MajorTopicYN="N" UI="Q000379">methods</QualifierName>
</MeshHeading>
<MeshHeading><DescriptorName MajorTopicYN="N" UI="D012680">Sensitivity and Specificity</DescriptorName>
</MeshHeading>
<MeshHeading><DescriptorName MajorTopicYN="N" UI="D012815">Signal Processing, Computer-Assisted</DescriptorName>
</MeshHeading>
</MeshHeadingList>
</MedlineCitation>
<PubmedData><History><PubMedPubDate PubStatus="pubmed"><Year>2004</Year>
<Month>9</Month>
<Day>21</Day>
<Hour>5</Hour>
<Minute>0</Minute>
</PubMedPubDate>
<PubMedPubDate PubStatus="medline"><Year>2004</Year>
<Month>10</Month>
<Day>13</Day>
<Hour>9</Hour>
<Minute>0</Minute>
</PubMedPubDate>
<PubMedPubDate PubStatus="entrez"><Year>2004</Year>
<Month>9</Month>
<Day>21</Day>
<Hour>5</Hour>
<Minute>0</Minute>
</PubMedPubDate>
</History>
<PublicationStatus>ppublish</PublicationStatus>
<ArticleIdList><ArticleId IdType="pubmed">15376960</ArticleId>
</ArticleIdList>
</PubmedData>
</pubmed>
<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><noCountry><name sortKey="Waibel, Alex" sort="Waibel, Alex" uniqKey="Waibel A" first="Alex" last="Waibel">Alex Waibel</name>
<name sortKey="Yang, Jie" sort="Yang, Jie" uniqKey="Yang J" first="Jie" last="Yang">Jie Yang</name>
<name sortKey="Zhang, Jing" sort="Zhang, Jing" uniqKey="Zhang J" first="Jing" last="Zhang">Jing Zhang</name>
</noCountry>
<country name="États-Unis"><region name="Pennsylvanie"><name sortKey="Chen, Xilin" sort="Chen, Xilin" uniqKey="Chen X" first="Xilin" last="Chen">Xilin Chen</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 000065 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/PubMed/Checkpoint/biblio.hfd -nk 000065 | 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:15376960 |texte= Automatic detection and recognition of signs from natural scenes. }}
Pour générer des pages wiki
HfdIndexSelect -h $EXPLOR_AREA/Data/PubMed/Checkpoint/RBID.i -Sk "pubmed:15376960" \ | HfdSelect -Kh $EXPLOR_AREA/Data/PubMed/Checkpoint/biblio.hfd \ | NlmPubMed2Wicri -a OcrV1
This area was generated with Dilib version V0.6.32. |