OcrV1, Main, Exploration, bibRecord, 001E46

Automatic news video caption extraction and recognition

Identifieur interne : 001E46 ( Main/Exploration ); précédent : 001E45; suivant : 001E47

Automatic news video caption extraction and recognition

Auteurs : XINBO GAO [Hong Kong] ; XIAOOU TANG [Hong Kong]

Source :

Lecture notes in computer science [ 0302-9743 ] ; 2000.

RBID : Pascal:01-0085666

Descripteurs français

Pascal (Inist)
- Image numérique, Production vidéo, Indexation, Chine, Extraction, Reconnaissance caractère, Sous titre, Caption.

English descriptors

KwdEn :
- Character recognition, China, Digital image, Extraction, Indexing, Subtitle, Video production.

Abstract

Caption graphically superimposed in news video frames can provide important indexing information. The automatic extraction and recognition of news captions can be of great help in querying topics of interest in a digital news video library. To develop such a system for Chinese news video, we present algorithms for detection, extraction, binarization and recognition of Chinese video captions. Experimental results show that our caption processing scheme is effective and robust and significantly improves video caption OCR results.

Affiliations:

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

to stream PascalFrancis, to step Corpus: 000737
to stream PascalFrancis, to step Curation: 000056
to stream PascalFrancis, to step Checkpoint: 000743
to stream Main, to step Merge: 001F55
to stream Main, to step Curation: 001E46

Le document en format XML

<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Automatic news video caption extraction and recognition</title>
<author><name sortKey="Xinbo Gao" sort="Xinbo Gao" uniqKey="Xinbo Gao" last="Xinbo Gao">XINBO GAO</name>
<affiliation wicri:level="4"><inist:fA14 i1="01"><s1>Department of Information Engineering, The Chinese University of Hong Kong</s1>
<s2>Shatin</s2>
<s3>HKG</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>Hong Kong</country>
<placeName><settlement type="city">Sha Tin</settlement>
</placeName>
<orgName type="university">Université chinoise de Hong Kong</orgName>
</affiliation>
</author>
<author><name sortKey="Xiaoou Tang" sort="Xiaoou Tang" uniqKey="Xiaoou Tang" last="Xiaoou Tang">XIAOOU TANG</name>
<affiliation wicri:level="4"><inist:fA14 i1="01"><s1>Department of Information Engineering, The Chinese University of Hong Kong</s1>
<s2>Shatin</s2>
<s3>HKG</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>Hong Kong</country>
<placeName><settlement type="city">Sha Tin</settlement>
</placeName>
<orgName type="university">Université chinoise de Hong Kong</orgName>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">01-0085666</idno>
<date when="2000">2000</date>
<idno type="stanalyst">PASCAL 01-0085666 INIST</idno>
<idno type="RBID">Pascal:01-0085666</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000737</idno>
<idno type="wicri:Area/PascalFrancis/Curation">000056</idno>
<idno type="wicri:Area/PascalFrancis/Checkpoint">000743</idno>
<idno type="wicri:doubleKey">0302-9743:2000:Xinbo Gao:automatic:news:video</idno>
<idno type="wicri:Area/Main/Merge">001F55</idno>
<idno type="wicri:Area/Main/Curation">001E46</idno>
<idno type="wicri:Area/Main/Exploration">001E46</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Automatic news video caption extraction and recognition</title>
<author><name sortKey="Xinbo Gao" sort="Xinbo Gao" uniqKey="Xinbo Gao" last="Xinbo Gao">XINBO GAO</name>
<affiliation wicri:level="4"><inist:fA14 i1="01"><s1>Department of Information Engineering, The Chinese University of Hong Kong</s1>
<s2>Shatin</s2>
<s3>HKG</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>Hong Kong</country>
<placeName><settlement type="city">Sha Tin</settlement>
</placeName>
<orgName type="university">Université chinoise de Hong Kong</orgName>
</affiliation>
</author>
<author><name sortKey="Xiaoou Tang" sort="Xiaoou Tang" uniqKey="Xiaoou Tang" last="Xiaoou Tang">XIAOOU TANG</name>
<affiliation wicri:level="4"><inist:fA14 i1="01"><s1>Department of Information Engineering, The Chinese University of Hong Kong</s1>
<s2>Shatin</s2>
<s3>HKG</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>Hong Kong</country>
<placeName><settlement type="city">Sha Tin</settlement>
</placeName>
<orgName type="university">Université chinoise de Hong Kong</orgName>
</affiliation>
</author>
</analytic>
<series><title level="j" type="main">Lecture notes in computer science</title>
<idno type="ISSN">0302-9743</idno>
<imprint><date when="2000">2000</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>China</term>
<term>Digital image</term>
<term>Extraction</term>
<term>Indexing</term>
<term>Subtitle</term>
<term>Video production</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Image numérique</term>
<term>Production vidéo</term>
<term>Indexation</term>
<term>Chine</term>
<term>Extraction</term>
<term>Reconnaissance caractère</term>
<term>Sous titre</term>
<term>Caption</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">Caption graphically superimposed in news video frames can provide important indexing information. The automatic extraction and recognition of news captions can be of great help in querying topics of interest in a digital news video library. To develop such a system for Chinese news video, we present algorithms for detection, extraction, binarization and recognition of Chinese video captions. Experimental results show that our caption processing scheme is effective and robust and significantly improves video caption OCR results.</div>
</front>
</TEI>
<affiliations><list><country><li>Hong Kong</li>
</country>
<settlement><li>Sha Tin</li>
</settlement>
<orgName><li>Université chinoise de Hong Kong</li>
</orgName>
</list>
<tree><country name="Hong Kong"><noRegion><name sortKey="Xinbo Gao" sort="Xinbo Gao" uniqKey="Xinbo Gao" last="Xinbo Gao">XINBO GAO</name>
</noRegion>
<name sortKey="Xiaoou Tang" sort="Xiaoou Tang" uniqKey="Xiaoou Tang" last="Xiaoou Tang">XIAOOU TANG</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 001E46 | SxmlIndent | more

HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 001E46 | 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:01-0085666
   |texte=   Automatic news video caption extraction and recognition
}}

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 news video caption extraction and recognition

Automatic news video caption extraction and recognition

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