Complementary combination of holistic and component analysis for recognition of low-resolution video character images
Identifieur interne : 000495 ( PascalFrancis/Curation ); précédent : 000494; suivant : 000496Complementary combination of holistic and component analysis for recognition of low-resolution video character images
Auteurs : Seonghun Lee [Corée du Sud] ; Jinhyung Kim [Corée du Sud]Source :
- Pattern recognition letters [ 0167-8655 ] ; 2008.
Descripteurs français
- Pascal (Inist)
English descriptors
- KwdEn :
Abstract
Video OCR aims at extracting text from video images in order to understand the context of the video. Video character images are usually given in low resolution with unique characteristics such as large stroke distortion, font variation, and variable size. Therefore, recognizing such characters in video images is very challenging. This is particularly true in the case of Chinese and Korean languages, where characters have complicated shapes and the number of classes (characters) is very large. In this paper, we propose a complementary combination of two recognizer approaches: a holistic approach and a component analysis. The holistic approach utilizes the global shape information of a character image to recognize a radical at a specific location of the character. On the contrary, the component analysis utilizes a detailed local shape of a segmented radical image to recognize the radical. The former is effective for character degradation whereas the latter is strong at processing ambiguous characters and font variations. In an evaluation of 50,000 video character images of Korean script, the proposed method achieved 96.5% accuracy. From this, we may draw a conclusion that the proposed method works well even with low quality images of complicated characters.
pA |
|
---|
Links toward previous steps (curation, corpus...)
- to stream PascalFrancis, to step Corpus: Pour aller vers cette notice dans l'étape Curation :000289
Links to Exploration step
Pascal:08-0105777Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Complementary combination of holistic and component analysis for recognition of low-resolution video character images</title>
<author><name sortKey="Lee, Seonghun" sort="Lee, Seonghun" uniqKey="Lee S" first="Seonghun" last="Lee">Seonghun Lee</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Department of Computer Science, KAIST, 373-1 Guseong-dong</s1>
<s2>Yuseong-gu, Daejeon</s2>
<s3>KOR</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>Corée du Sud</country>
</affiliation>
</author>
<author><name sortKey="Kim, Jinhyung" sort="Kim, Jinhyung" uniqKey="Kim J" first="Jinhyung" last="Kim">Jinhyung Kim</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Department of Computer Science, KAIST, 373-1 Guseong-dong</s1>
<s2>Yuseong-gu, Daejeon</s2>
<s3>KOR</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>Corée du Sud</country>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">08-0105777</idno>
<date when="2008">2008</date>
<idno type="stanalyst">PASCAL 08-0105777 INIST</idno>
<idno type="RBID">Pascal:08-0105777</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000289</idno>
<idno type="wicri:Area/PascalFrancis/Curation">000495</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Complementary combination of holistic and component analysis for recognition of low-resolution video character images</title>
<author><name sortKey="Lee, Seonghun" sort="Lee, Seonghun" uniqKey="Lee S" first="Seonghun" last="Lee">Seonghun Lee</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Department of Computer Science, KAIST, 373-1 Guseong-dong</s1>
<s2>Yuseong-gu, Daejeon</s2>
<s3>KOR</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>Corée du Sud</country>
</affiliation>
</author>
<author><name sortKey="Kim, Jinhyung" sort="Kim, Jinhyung" uniqKey="Kim J" first="Jinhyung" last="Kim">Jinhyung Kim</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Department of Computer Science, KAIST, 373-1 Guseong-dong</s1>
<s2>Yuseong-gu, Daejeon</s2>
<s3>KOR</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>Corée du Sud</country>
</affiliation>
</author>
</analytic>
<series><title level="j" type="main">Pattern recognition letters</title>
<title level="j" type="abbreviated">Pattern recogn. lett.</title>
<idno type="ISSN">0167-8655</idno>
<imprint><date when="2008">2008</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><title level="j" type="main">Pattern recognition letters</title>
<title level="j" type="abbreviated">Pattern recogn. lett.</title>
<idno type="ISSN">0167-8655</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Accuracy</term>
<term>Character recognition</term>
<term>Chinese</term>
<term>Degradation</term>
<term>Image processing</term>
<term>Image segmentation</term>
<term>Korean</term>
<term>Localization</term>
<term>Low resolution</term>
<term>Optical character recognition</term>
<term>Pattern recognition</term>
<term>Signal classification</term>
<term>Support vector machine</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Basse résolution</term>
<term>Reconnaissance optique caractère</term>
<term>Chinois</term>
<term>Coréen</term>
<term>Localisation</term>
<term>Segmentation image</term>
<term>Dégradation</term>
<term>Précision</term>
<term>Reconnaissance caractère</term>
<term>Machine vecteur support</term>
<term>Reconnaissance forme</term>
<term>Traitement image</term>
<term>Classification signal</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">Video OCR aims at extracting text from video images in order to understand the context of the video. Video character images are usually given in low resolution with unique characteristics such as large stroke distortion, font variation, and variable size. Therefore, recognizing such characters in video images is very challenging. This is particularly true in the case of Chinese and Korean languages, where characters have complicated shapes and the number of classes (characters) is very large. In this paper, we propose a complementary combination of two recognizer approaches: a holistic approach and a component analysis. The holistic approach utilizes the global shape information of a character image to recognize a radical at a specific location of the character. On the contrary, the component analysis utilizes a detailed local shape of a segmented radical image to recognize the radical. The former is effective for character degradation whereas the latter is strong at processing ambiguous characters and font variations. In an evaluation of 50,000 video character images of Korean script, the proposed method achieved 96.5% accuracy. From this, we may draw a conclusion that the proposed method works well even with low quality images of complicated characters.</div>
</front>
</TEI>
<inist><standard h6="B"><pA><fA01 i1="01" i2="1"><s0>0167-8655</s0>
</fA01>
<fA02 i1="01"><s0>PRLEDG</s0>
</fA02>
<fA03 i2="1"><s0>Pattern recogn. lett.</s0>
</fA03>
<fA05><s2>29</s2>
</fA05>
<fA06><s2>4</s2>
</fA06>
<fA08 i1="01" i2="1" l="ENG"><s1>Complementary combination of holistic and component analysis for recognition of low-resolution video character images</s1>
</fA08>
<fA11 i1="01" i2="1"><s1>LEE (Seonghun)</s1>
</fA11>
<fA11 i1="02" i2="1"><s1>KIM (Jinhyung)</s1>
</fA11>
<fA14 i1="01"><s1>Department of Computer Science, KAIST, 373-1 Guseong-dong</s1>
<s2>Yuseong-gu, Daejeon</s2>
<s3>KOR</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</fA14>
<fA20><s1>383-391</s1>
</fA20>
<fA21><s1>2008</s1>
</fA21>
<fA23 i1="01"><s0>ENG</s0>
</fA23>
<fA43 i1="01"><s1>INIST</s1>
<s2>20222</s2>
<s5>354000174598360010</s5>
</fA43>
<fA44><s0>0000</s0>
<s1>© 2008 INIST-CNRS. All rights reserved.</s1>
</fA44>
<fA45><s0>1/4 p.</s0>
</fA45>
<fA47 i1="01" i2="1"><s0>08-0105777</s0>
</fA47>
<fA60><s1>P</s1>
</fA60>
<fA61><s0>A</s0>
</fA61>
<fA64 i1="01" i2="1"><s0>Pattern recognition letters</s0>
</fA64>
<fA66 i1="01"><s0>NLD</s0>
</fA66>
<fC01 i1="01" l="ENG"><s0>Video OCR aims at extracting text from video images in order to understand the context of the video. Video character images are usually given in low resolution with unique characteristics such as large stroke distortion, font variation, and variable size. Therefore, recognizing such characters in video images is very challenging. This is particularly true in the case of Chinese and Korean languages, where characters have complicated shapes and the number of classes (characters) is very large. In this paper, we propose a complementary combination of two recognizer approaches: a holistic approach and a component analysis. The holistic approach utilizes the global shape information of a character image to recognize a radical at a specific location of the character. On the contrary, the component analysis utilizes a detailed local shape of a segmented radical image to recognize the radical. The former is effective for character degradation whereas the latter is strong at processing ambiguous characters and font variations. In an evaluation of 50,000 video character images of Korean script, the proposed method achieved 96.5% accuracy. From this, we may draw a conclusion that the proposed method works well even with low quality images of complicated characters.</s0>
</fC01>
<fC02 i1="01" i2="X"><s0>001D04A05A</s0>
</fC02>
<fC02 i1="02" i2="X"><s0>001D04A05C</s0>
</fC02>
<fC02 i1="03" i2="X"><s0>001D04A04A1</s0>
</fC02>
<fC03 i1="01" i2="X" l="FRE"><s0>Basse résolution</s0>
<s5>01</s5>
</fC03>
<fC03 i1="01" i2="X" l="ENG"><s0>Low resolution</s0>
<s5>01</s5>
</fC03>
<fC03 i1="01" i2="X" l="SPA"><s0>Baja resolución</s0>
<s5>01</s5>
</fC03>
<fC03 i1="02" i2="X" l="FRE"><s0>Reconnaissance optique caractère</s0>
<s5>02</s5>
</fC03>
<fC03 i1="02" i2="X" l="ENG"><s0>Optical character recognition</s0>
<s5>02</s5>
</fC03>
<fC03 i1="02" i2="X" l="SPA"><s0>Reconocimento óptico de caracteres</s0>
<s5>02</s5>
</fC03>
<fC03 i1="03" i2="X" l="FRE"><s0>Chinois</s0>
<s5>03</s5>
</fC03>
<fC03 i1="03" i2="X" l="ENG"><s0>Chinese</s0>
<s5>03</s5>
</fC03>
<fC03 i1="03" i2="X" l="SPA"><s0>Chino</s0>
<s5>03</s5>
</fC03>
<fC03 i1="04" i2="X" l="FRE"><s0>Coréen</s0>
<s5>04</s5>
</fC03>
<fC03 i1="04" i2="X" l="ENG"><s0>Korean</s0>
<s5>04</s5>
</fC03>
<fC03 i1="04" i2="X" l="SPA"><s0>Coreano</s0>
<s5>04</s5>
</fC03>
<fC03 i1="05" i2="X" l="FRE"><s0>Localisation</s0>
<s5>05</s5>
</fC03>
<fC03 i1="05" i2="X" l="ENG"><s0>Localization</s0>
<s5>05</s5>
</fC03>
<fC03 i1="05" i2="X" l="SPA"><s0>Localización</s0>
<s5>05</s5>
</fC03>
<fC03 i1="06" i2="3" l="FRE"><s0>Segmentation image</s0>
<s5>06</s5>
</fC03>
<fC03 i1="06" i2="3" l="ENG"><s0>Image segmentation</s0>
<s5>06</s5>
</fC03>
<fC03 i1="07" i2="X" l="FRE"><s0>Dégradation</s0>
<s5>07</s5>
</fC03>
<fC03 i1="07" i2="X" l="ENG"><s0>Degradation</s0>
<s5>07</s5>
</fC03>
<fC03 i1="07" i2="X" l="SPA"><s0>Degradación</s0>
<s5>07</s5>
</fC03>
<fC03 i1="08" i2="X" l="FRE"><s0>Précision</s0>
<s5>08</s5>
</fC03>
<fC03 i1="08" i2="X" l="ENG"><s0>Accuracy</s0>
<s5>08</s5>
</fC03>
<fC03 i1="08" i2="X" l="SPA"><s0>Precisión</s0>
<s5>08</s5>
</fC03>
<fC03 i1="09" i2="X" l="FRE"><s0>Reconnaissance caractère</s0>
<s5>09</s5>
</fC03>
<fC03 i1="09" i2="X" l="ENG"><s0>Character recognition</s0>
<s5>09</s5>
</fC03>
<fC03 i1="09" i2="X" l="SPA"><s0>Reconocimiento carácter</s0>
<s5>09</s5>
</fC03>
<fC03 i1="10" i2="X" l="FRE"><s0>Machine vecteur support</s0>
<s5>10</s5>
</fC03>
<fC03 i1="10" i2="X" l="ENG"><s0>Support vector machine</s0>
<s5>10</s5>
</fC03>
<fC03 i1="10" i2="X" l="SPA"><s0>Máquina vector soporte</s0>
<s5>10</s5>
</fC03>
<fC03 i1="11" i2="X" l="FRE"><s0>Reconnaissance forme</s0>
<s5>31</s5>
</fC03>
<fC03 i1="11" i2="X" l="ENG"><s0>Pattern recognition</s0>
<s5>31</s5>
</fC03>
<fC03 i1="11" i2="X" l="SPA"><s0>Reconocimiento patrón</s0>
<s5>31</s5>
</fC03>
<fC03 i1="12" i2="X" l="FRE"><s0>Traitement image</s0>
<s5>32</s5>
</fC03>
<fC03 i1="12" i2="X" l="ENG"><s0>Image processing</s0>
<s5>32</s5>
</fC03>
<fC03 i1="12" i2="X" l="SPA"><s0>Procesamiento imagen</s0>
<s5>32</s5>
</fC03>
<fC03 i1="13" i2="3" l="FRE"><s0>Classification signal</s0>
<s5>33</s5>
</fC03>
<fC03 i1="13" i2="3" l="ENG"><s0>Signal classification</s0>
<s5>33</s5>
</fC03>
<fN21><s1>056</s1>
</fN21>
<fN44 i1="01"><s1>OTO</s1>
</fN44>
<fN82><s1>OTO</s1>
</fN82>
</pA>
</standard>
</inist>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/PascalFrancis/Curation
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000495 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/PascalFrancis/Curation/biblio.hfd -nk 000495 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Ticri/CIDE |area= OcrV1 |flux= PascalFrancis |étape= Curation |type= RBID |clé= Pascal:08-0105777 |texte= Complementary combination of holistic and component analysis for recognition of low-resolution video character images }}
This area was generated with Dilib version V0.6.32. |