A robust video text extraction method for character recognition
Identifieur interne : 001347 ( Main/Exploration ); précédent : 001346; suivant : 001348A robust video text extraction method for character recognition
Auteurs : Osamu Hori [Japon] ; Takeshi Mita [Japon]Source :
- Systems and Computers in Japan [ 0882-1666 ] ; 2005-08.
English descriptors
Abstract
This paper proposes a method for extracting text portions occurring in video images with high accuracy for reading by OCR. Past studies have produced methods of extracting text in a video image from its background by binarization based on a threshold, utilizing the fact that the intensity of the text is higher than that of the background. One method for determining the threshold is Shio's application of Otsu's method, assuming the distribution of two intensities of the background and characters in local blocks. However, methods based on various intensities of the background such as those of video images have the problem of not yielding a good threshold due to assumptions that are not necessarily valid. In addition, in reality, they cannot extract characters with accuracy sufficient for OCR readability because the intensity around the characters is not necessarily high due to the effects of shadowing, edge elimination, and signal conversion processing. Thus, this paper proposes a method of extracting only the text portions by robustly estimating the intensity distribution of the text portions, initially extracting high‐reliability areas as text portions, and extending the areas based on the estimated distribution. Experimental results show that the proposed method extracts text portions with higher accuracy and better OCR readability than the conventional methods. © 2005 Wiley Periodicals, Inc. Syst Comp Jpn, 36(9): 87–96, 2005; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/scj.10148
Url:
DOI: 10.1002/scj.10148
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 000066
- to stream Istex, to step Curation: 000065
- to stream Istex, to step Checkpoint: 000C56
- to stream Main, to step Merge: 001383
- to stream Main, to step Curation: 001347
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">A robust video text extraction method for character recognition</title><author><name sortKey="Hori, Osamu" sort="Hori, Osamu" uniqKey="Hori O" first="Osamu" last="Hori">Osamu Hori</name></author><author><name sortKey="Mita, Takeshi" sort="Mita, Takeshi" uniqKey="Mita T" first="Takeshi" last="Mita">Takeshi Mita</name></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:FA8AF07F375EF38674858FDE24E96596F21AF16F</idno><date when="2005" year="2005">2005</date><idno type="doi">10.1002/scj.10148</idno><idno type="url">https://api.istex.fr/document/FA8AF07F375EF38674858FDE24E96596F21AF16F/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">000066</idno><idno type="wicri:Area/Istex/Curation">000065</idno><idno type="wicri:Area/Istex/Checkpoint">000C56</idno><idno type="wicri:doubleKey">0882-1666:2005:Hori O:a:robust:video</idno><idno type="wicri:Area/Main/Merge">001383</idno><idno type="wicri:Area/Main/Curation">001347</idno><idno type="wicri:Area/Main/Exploration">001347</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">A robust video text extraction method for character recognition</title><author><name sortKey="Hori, Osamu" sort="Hori, Osamu" uniqKey="Hori O" first="Osamu" last="Hori">Osamu Hori</name><affiliation wicri:level="1"><country xml:lang="fr">Japon</country><wicri:regionArea>Corporate R&D Center, Multimedia Laboratory, Toshiba Corporation, Kawasaki</wicri:regionArea><wicri:noRegion>Kawasaki</wicri:noRegion></affiliation></author><author><name sortKey="Mita, Takeshi" sort="Mita, Takeshi" uniqKey="Mita T" first="Takeshi" last="Mita">Takeshi Mita</name><affiliation wicri:level="1"><country xml:lang="fr">Japon</country><wicri:regionArea>Corporate R&D Center, Multimedia Laboratory, Toshiba Corporation, Kawasaki</wicri:regionArea><wicri:noRegion>Kawasaki</wicri:noRegion></affiliation></author></analytic><monogr></monogr><series><title level="j">Systems and Computers in Japan</title><title level="j" type="abbrev">Syst. Comp. Jpn.</title><idno type="ISSN">0882-1666</idno><idno type="eISSN">1520-684X</idno><imprint><publisher>Wiley Subscription Services, Inc., A Wiley Company</publisher><pubPlace>Hoboken</pubPlace><date type="published" when="2005-08">2005-08</date><biblScope unit="volume">36</biblScope><biblScope unit="issue">9</biblScope><biblScope unit="page" from="87">87</biblScope><biblScope unit="page" to="96">96</biblScope></imprint><idno type="ISSN">0882-1666</idno></series><idno type="istex">FA8AF07F375EF38674858FDE24E96596F21AF16F</idno><idno type="DOI">10.1002/scj.10148</idno><idno type="ArticleID">SCJ10148</idno></biblStruct></sourceDesc><seriesStmt><idno type="ISSN">0882-1666</idno></seriesStmt></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>OCR</term><term>text portion extraction</term><term>video image processing</term><term>videotext recognition</term></keywords></textClass><langUsage><language ident="en">en</language></langUsage></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">This paper proposes a method for extracting text portions occurring in video images with high accuracy for reading by OCR. Past studies have produced methods of extracting text in a video image from its background by binarization based on a threshold, utilizing the fact that the intensity of the text is higher than that of the background. One method for determining the threshold is Shio's application of Otsu's method, assuming the distribution of two intensities of the background and characters in local blocks. However, methods based on various intensities of the background such as those of video images have the problem of not yielding a good threshold due to assumptions that are not necessarily valid. In addition, in reality, they cannot extract characters with accuracy sufficient for OCR readability because the intensity around the characters is not necessarily high due to the effects of shadowing, edge elimination, and signal conversion processing. Thus, this paper proposes a method of extracting only the text portions by robustly estimating the intensity distribution of the text portions, initially extracting high‐reliability areas as text portions, and extending the areas based on the estimated distribution. Experimental results show that the proposed method extracts text portions with higher accuracy and better OCR readability than the conventional methods. © 2005 Wiley Periodicals, Inc. Syst Comp Jpn, 36(9): 87–96, 2005; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/scj.10148</div></front></TEI><affiliations><list><country><li>Japon</li></country></list><tree><country name="Japon"><noRegion><name sortKey="Hori, Osamu" sort="Hori, Osamu" uniqKey="Hori O" first="Osamu" last="Hori">Osamu Hori</name></noRegion><name sortKey="Mita, Takeshi" sort="Mita, Takeshi" uniqKey="Mita T" first="Takeshi" last="Mita">Takeshi Mita</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 001347 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 001347 | 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= ISTEX:FA8AF07F375EF38674858FDE24E96596F21AF16F
|texte= A robust video text extraction method for character recognition
}}
| This area was generated with Dilib version V0.6.32. |  |