An automatic system for text location and extraction in digital video based using SVM
Identifieur interne : 001718 ( Main/Merge ); précédent : 001717; suivant : 001719An automatic system for text location and extraction in digital video based using SVM
Auteurs : Zhiguo Cheng [République populaire de Chine] ; Yuncai Liu [République populaire de Chine]Source :
Descripteurs français
- Pascal (Inist)
- Système automatique, Localisation, Signal numérique, Signal vidéo, Machine vecteur support, Source information, Codage vidéo, Segmentation image, Reconnaissance optique caractère, Classification signal, Traitement signal vidéo, Traitement image, Reconnaissance forme, Extraction caractéristique, Traitement signal.
English descriptors
- KwdEn :
Abstract
Text that appears in a scene or is graphically added to video can provide an important supplemental source of index information as well as clues for decoding the video's structure and for classification. In this work. a novel algoritlun is present for detecting and locating text in digital video. The first module of the system divides an image into small blocks which are featured by pixel value and are fed to SVM (Support Vector Machine) to classify text blocks or not. The other module is to do post-processing on the classified text blocks to identify the rectangle region of them and OCR can be used further easily. Experiments conducted with a variety of video sources showed that our method could detect and locate text region successfully by SVM with comparatively less samples.
Links toward previous steps (curation, corpus...)
- to stream PascalFrancis, to step Corpus: 000368
- to stream PascalFrancis, to step Curation: 000418
- to stream PascalFrancis, to step Checkpoint: 000507
Links to Exploration step
Pascal:06-0453353Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">An automatic system for text location and extraction in digital video based using SVM</title>
<author><name sortKey="Cheng, Zhiguo" sort="Cheng, Zhiguo" uniqKey="Cheng Z" first="Zhiguo" last="Cheng">Zhiguo Cheng</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Institute of Image Processing and Pattern Recognition, Shanghai Jiaotong University</s1>
<s2>Shanghai 200030</s2>
<s3>CHN</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>République populaire de Chine</country>
<wicri:noRegion>Shanghai 200030</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Liu, Yuncai" sort="Liu, Yuncai" uniqKey="Liu Y" first="Yuncai" last="Liu">Yuncai Liu</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Institute of Image Processing and Pattern Recognition, Shanghai Jiaotong University</s1>
<s2>Shanghai 200030</s2>
<s3>CHN</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>République populaire de Chine</country>
<wicri:noRegion>Shanghai 200030</wicri:noRegion>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">06-0453353</idno>
<date when="2004">2004</date>
<idno type="stanalyst">PASCAL 06-0453353 INIST</idno>
<idno type="RBID">Pascal:06-0453353</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000368</idno>
<idno type="wicri:Area/PascalFrancis/Curation">000418</idno>
<idno type="wicri:Area/PascalFrancis/Checkpoint">000507</idno>
<idno type="wicri:Area/Main/Merge">001718</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">An automatic system for text location and extraction in digital video based using SVM</title>
<author><name sortKey="Cheng, Zhiguo" sort="Cheng, Zhiguo" uniqKey="Cheng Z" first="Zhiguo" last="Cheng">Zhiguo Cheng</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Institute of Image Processing and Pattern Recognition, Shanghai Jiaotong University</s1>
<s2>Shanghai 200030</s2>
<s3>CHN</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>République populaire de Chine</country>
<wicri:noRegion>Shanghai 200030</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Liu, Yuncai" sort="Liu, Yuncai" uniqKey="Liu Y" first="Yuncai" last="Liu">Yuncai Liu</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Institute of Image Processing and Pattern Recognition, Shanghai Jiaotong University</s1>
<s2>Shanghai 200030</s2>
<s3>CHN</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>République populaire de Chine</country>
<wicri:noRegion>Shanghai 200030</wicri:noRegion>
</affiliation>
</author>
</analytic>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Automatic system</term>
<term>Digital signal</term>
<term>Feature extraction</term>
<term>Image processing</term>
<term>Image segmentation</term>
<term>Information source</term>
<term>Localization</term>
<term>Optical character recognition</term>
<term>Pattern recognition</term>
<term>Signal classification</term>
<term>Signal processing</term>
<term>Support vector machine</term>
<term>Video coding</term>
<term>Video signal</term>
<term>Video signal processing</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Système automatique</term>
<term>Localisation</term>
<term>Signal numérique</term>
<term>Signal vidéo</term>
<term>Machine vecteur support</term>
<term>Source information</term>
<term>Codage vidéo</term>
<term>Segmentation image</term>
<term>Reconnaissance optique caractère</term>
<term>Classification signal</term>
<term>Traitement signal vidéo</term>
<term>Traitement image</term>
<term>Reconnaissance forme</term>
<term>Extraction caractéristique</term>
<term>Traitement signal</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">Text that appears in a scene or is graphically added to video can provide an important supplemental source of index information as well as clues for decoding the video's structure and for classification. In this work. a novel algoritlun is present for detecting and locating text in digital video. The first module of the system divides an image into small blocks which are featured by pixel value and are fed to SVM (Support Vector Machine) to classify text blocks or not. The other module is to do post-processing on the classified text blocks to identify the rectangle region of them and OCR can be used further easily. Experiments conducted with a variety of video sources showed that our method could detect and locate text region successfully by SVM with comparatively less samples.</div>
</front>
</TEI>
<affiliations><list><country><li>République populaire de Chine</li>
</country>
</list>
<tree><country name="République populaire de Chine"><noRegion><name sortKey="Cheng, Zhiguo" sort="Cheng, Zhiguo" uniqKey="Cheng Z" first="Zhiguo" last="Cheng">Zhiguo Cheng</name>
</noRegion>
<name sortKey="Liu, Yuncai" sort="Liu, Yuncai" uniqKey="Liu Y" first="Yuncai" last="Liu">Yuncai Liu</name>
</country>
</tree>
</affiliations>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/Main/Merge
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 001718 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Merge/biblio.hfd -nk 001718 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Ticri/CIDE |area= OcrV1 |flux= Main |étape= Merge |type= RBID |clé= Pascal:06-0453353 |texte= An automatic system for text location and extraction in digital video based using SVM }}
This area was generated with Dilib version V0.6.32. |