OcrV1, Main, Exploration, bibRecord, 001370

Text detection and recognition for video indexing

Identifieur interne : 001370 ( Main/Exploration ); précédent : 001369; suivant : 001371

Text detection and recognition for video indexing

Auteurs : ARISH ASIF QAZI [Allemagne] ; Imran A. Siddiqi [Pakistan] ; M. Sarmad Hussain [Pakistan]

Source :

RBID : Pascal:06-0213101

Descripteurs français

Pascal (Inist)
- Reconnaissance caractère, Indexation, Recherche information, Signal numérique, Signal vidéo, Analyse sémantique, Base connaissance, Recherche image, Localisation, Reconnaissance optique caractère, Packaging électronique, Reconnaissance forme, Extraction caractéristique, Traitement signal.

English descriptors

KwdEn :
- Character recognition, Digital signal, Electronic packaging, Feature extraction, Image retrieval, Indexing, Information retrieval, Knowledge base, Localization, Optical character recognition, Pattern recognition, Semantic analysis, Signal processing, Video signal.

Abstract

Efficient indexing and retrieval of digital video has been an area of active research in the recent years. Many of the existing retrieval systems, however, work without semantic knowledge. We propose a knowledge-based approach for video indexing, based on the fact that videos are rich in semantic contents. The most powerful index for semantic retrieval of video images is the Text appearing in them. In this paper we present a system for localization of horizontally aligned artificial text in video images. The detected text is binarized and is passed to a standard OCR package. The system has been thoroughly tested and the experimental results are found to be quite encouraging.

Affiliations:

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

to stream PascalFrancis, to step Corpus: 000394
to stream PascalFrancis, to step Curation: 000392
to stream PascalFrancis, to step Checkpoint: 000377
to stream Main, to step Merge: 001407
to stream Main, to step Curation: 001370

Le document en format XML

<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Text detection and recognition for video indexing</title>
<author><name sortKey="Arish Asif Qazi" sort="Arish Asif Qazi" uniqKey="Arish Asif Qazi" last="Arish Asif Qazi">ARISH ASIF QAZI</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Room No 617 SpannsKamp26</s1>
<s2>22527 Hamburg</s2>
<s3>DEU</s3>
<sZ>1 aut.</sZ>
</inist:fA14>
<country>Allemagne</country>
<wicri:noRegion>22527 Hamburg</wicri:noRegion>
<placeName><settlement type="city">Hambourg</settlement>
<region type="land" nuts="2">Hambourg</region>
</placeName>
</affiliation>
</author>
<author><name sortKey="Siddiqi, Imran A" sort="Siddiqi, Imran A" uniqKey="Siddiqi I" first="Imran A." last="Siddiqi">Imran A. Siddiqi</name>
<affiliation wicri:level="1"><inist:fA14 i1="02"><s1>InterActive Communications Private Limited* 9 - Street 29, F-7/1</s1>
<s2>Islamabad</s2>
<s3>PAK</s3>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>Pakistan</country>
<wicri:noRegion>Islamabad</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Sarmad Hussain, M" sort="Sarmad Hussain, M" uniqKey="Sarmad Hussain M" first="M." last="Sarmad Hussain">M. Sarmad Hussain</name>
<affiliation wicri:level="1"><inist:fA14 i1="02"><s1>InterActive Communications Private Limited* 9 - Street 29, F-7/1</s1>
<s2>Islamabad</s2>
<s3>PAK</s3>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>Pakistan</country>
<wicri:noRegion>Islamabad</wicri:noRegion>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">06-0213101</idno>
<date when="2005">2005</date>
<idno type="stanalyst">PASCAL 06-0213101 INIST</idno>
<idno type="RBID">Pascal:06-0213101</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000394</idno>
<idno type="wicri:Area/PascalFrancis/Curation">000392</idno>
<idno type="wicri:Area/PascalFrancis/Checkpoint">000377</idno>
<idno type="wicri:Area/Main/Merge">001407</idno>
<idno type="wicri:Area/Main/Curation">001370</idno>
<idno type="wicri:Area/Main/Exploration">001370</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Text detection and recognition for video indexing</title>
<author><name sortKey="Arish Asif Qazi" sort="Arish Asif Qazi" uniqKey="Arish Asif Qazi" last="Arish Asif Qazi">ARISH ASIF QAZI</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Room No 617 SpannsKamp26</s1>
<s2>22527 Hamburg</s2>
<s3>DEU</s3>
<sZ>1 aut.</sZ>
</inist:fA14>
<country>Allemagne</country>
<wicri:noRegion>22527 Hamburg</wicri:noRegion>
<placeName><settlement type="city">Hambourg</settlement>
<region type="land" nuts="2">Hambourg</region>
</placeName>
</affiliation>
</author>
<author><name sortKey="Siddiqi, Imran A" sort="Siddiqi, Imran A" uniqKey="Siddiqi I" first="Imran A." last="Siddiqi">Imran A. Siddiqi</name>
<affiliation wicri:level="1"><inist:fA14 i1="02"><s1>InterActive Communications Private Limited* 9 - Street 29, F-7/1</s1>
<s2>Islamabad</s2>
<s3>PAK</s3>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>Pakistan</country>
<wicri:noRegion>Islamabad</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Sarmad Hussain, M" sort="Sarmad Hussain, M" uniqKey="Sarmad Hussain M" first="M." last="Sarmad Hussain">M. Sarmad Hussain</name>
<affiliation wicri:level="1"><inist:fA14 i1="02"><s1>InterActive Communications Private Limited* 9 - Street 29, F-7/1</s1>
<s2>Islamabad</s2>
<s3>PAK</s3>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>Pakistan</country>
<wicri:noRegion>Islamabad</wicri:noRegion>
</affiliation>
</author>
</analytic>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Character recognition</term>
<term>Digital signal</term>
<term>Electronic packaging</term>
<term>Feature extraction</term>
<term>Image retrieval</term>
<term>Indexing</term>
<term>Information retrieval</term>
<term>Knowledge base</term>
<term>Localization</term>
<term>Optical character recognition</term>
<term>Pattern recognition</term>
<term>Semantic analysis</term>
<term>Signal processing</term>
<term>Video signal</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Reconnaissance caractère</term>
<term>Indexation</term>
<term>Recherche information</term>
<term>Signal numérique</term>
<term>Signal vidéo</term>
<term>Analyse sémantique</term>
<term>Base connaissance</term>
<term>Recherche image</term>
<term>Localisation</term>
<term>Reconnaissance optique caractère</term>
<term>Packaging électronique</term>
<term>Reconnaissance forme</term>
<term>Extraction caractéristique</term>
<term>Traitement signal</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">Efficient indexing and retrieval of digital video has been an area of active research in the recent years. Many of the existing retrieval systems, however, work without semantic knowledge. We propose a knowledge-based approach for video indexing, based on the fact that videos are rich in semantic contents. The most powerful index for semantic retrieval of video images is the Text appearing in them. In this paper we present a system for localization of horizontally aligned artificial text in video images. The detected text is binarized and is passed to a standard OCR package. The system has been thoroughly tested and the experimental results are found to be quite encouraging.</div>
</front>
</TEI>
<affiliations><list><country><li>Allemagne</li>
<li>Pakistan</li>
</country>
<region><li>Hambourg</li>
</region>
<settlement><li>Hambourg</li>
</settlement>
</list>
<tree><country name="Allemagne"><region name="Hambourg"><name sortKey="Arish Asif Qazi" sort="Arish Asif Qazi" uniqKey="Arish Asif Qazi" last="Arish Asif Qazi">ARISH ASIF QAZI</name>
</region>
</country>
<country name="Pakistan"><noRegion><name sortKey="Siddiqi, Imran A" sort="Siddiqi, Imran A" uniqKey="Siddiqi I" first="Imran A." last="Siddiqi">Imran A. Siddiqi</name>
</noRegion>
<name sortKey="Sarmad Hussain, M" sort="Sarmad Hussain, M" uniqKey="Sarmad Hussain M" first="M." last="Sarmad Hussain">M. Sarmad Hussain</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 001370 | SxmlIndent | more

HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 001370 | 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:06-0213101
   |texte=   Text detection and recognition for video indexing
}}

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

Text detection and recognition for video indexing

Text detection and recognition for video indexing

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