Color Clustering Text Extraction Algorithm for Mobile Phone Images
Identifieur interne : 000792 ( Main/Exploration ); précédent : 000791; suivant : 000793Color Clustering Text Extraction Algorithm for Mobile Phone Images
Auteurs : Adrián Canedo-Rodriguez [Espagne] ; JUNG HYOUN KIM [États-Unis] ; John Kelly [États-Unis] ; JUNG HEE KIM [États-Unis] ; Soo-Hyung Kim [Corée du Sud] ; Yolanda Blanco-Fernindez [Espagne] ; Pavan Banugondi [États-Unis]Source :
Descripteurs français
- Pascal (Inist)
English descriptors
- KwdEn :
Abstract
Variety of approaches for text information extraction from images or video clips have been proposed so far, but none of them is suitable to be implemented over a low computational device, either because of their low accuracy, or slow performance. In this scenario, we propose a Text Extraction algorithm that extracts the text data within natural scene images taken with mobile phone, fast and accurately. The algorithm uses very efficient computations to calculate the Principal Color Components of a quantized image, and separates the main foreground-background colors, after which it extracts the text on the image. We have compared our algorithm with the Otsu algorithm by the use of a commercial OCR, achieving accuracy rates 12% higher, and performing 2 times faster than those algorithms. The proposed approach will be robust against common degradations, such as uneven illumination, or blurring. Therefore, this will be a very attractive algorithm that accurately separates foreground and background from scene text images and works effciently over low computational resources devices.
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream PascalFrancis, to step Corpus: 000090
- to stream PascalFrancis, to step Curation: 000682
- to stream PascalFrancis, to step Checkpoint: 000166
- to stream Main, to step Merge: 000797
- to stream Main, to step Curation: 000792
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Color Clustering Text Extraction Algorithm for Mobile Phone Images</title><author><name sortKey="Canedo Rodriguez, Adrian" sort="Canedo Rodriguez, Adrian" uniqKey="Canedo Rodriguez A" first="Adrián" last="Canedo-Rodriguez">Adrián Canedo-Rodriguez</name><affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Telematics Engineering Department, University of Vigo</s1><s3>ESP</s3><sZ>1 aut.</sZ><sZ>6 aut.</sZ></inist:fA14><country>Espagne</country><wicri:noRegion>Telematics Engineering Department, University of Vigo</wicri:noRegion></affiliation></author><author><name sortKey="Jung Hyoun Kim" sort="Jung Hyoun Kim" uniqKey="Jung Hyoun Kim" last="Jung Hyoun Kim">JUNG HYOUN KIM</name><affiliation wicri:level="2"><inist:fA14 i1="02"><s1>Electrical & Computer Engineering Department, NC A&T State University</s1><s2>Greensboro, NC</s2><s3>USA</s3><sZ>2 aut.</sZ><sZ>3 aut.</sZ><sZ>7 aut.</sZ></inist:fA14><country>États-Unis</country><placeName><region type="state">Caroline du Nord</region></placeName></affiliation></author><author><name sortKey="Kelly, John" sort="Kelly, John" uniqKey="Kelly J" first="John" last="Kelly">John Kelly</name><affiliation wicri:level="2"><inist:fA14 i1="02"><s1>Electrical & Computer Engineering Department, NC A&T State University</s1><s2>Greensboro, NC</s2><s3>USA</s3><sZ>2 aut.</sZ><sZ>3 aut.</sZ><sZ>7 aut.</sZ></inist:fA14><country>États-Unis</country><placeName><region type="state">Caroline du Nord</region></placeName></affiliation></author><author><name sortKey="Jung Hee Kim" sort="Jung Hee Kim" uniqKey="Jung Hee Kim" last="Jung Hee Kim">JUNG HEE KIM</name><affiliation wicri:level="2"><inist:fA14 i1="03"><s1>Computer Science Department, NC A&T State University</s1><s2>Greensboro, NC</s2><s3>USA</s3><sZ>4 aut.</sZ></inist:fA14><country>États-Unis</country><placeName><region type="state">Caroline du Nord</region></placeName></affiliation></author><author><name sortKey="Kim, Soo Hyung" sort="Kim, Soo Hyung" uniqKey="Kim S" first="Soo-Hyung" last="Kim">Soo-Hyung Kim</name><affiliation wicri:level="1"><inist:fA14 i1="04"><s1>Computer Science Department, Chonnam National University</s1><s3>KOR</s3><sZ>5 aut.</sZ></inist:fA14><country>Corée du Sud</country><wicri:noRegion>Computer Science Department, Chonnam National University</wicri:noRegion></affiliation></author><author><name sortKey="Blanco Fernindez, Yolanda" sort="Blanco Fernindez, Yolanda" uniqKey="Blanco Fernindez Y" first="Yolanda" last="Blanco-Fernindez">Yolanda Blanco-Fernindez</name><affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Telematics Engineering Department, University of Vigo</s1><s3>ESP</s3><sZ>1 aut.</sZ><sZ>6 aut.</sZ></inist:fA14><country>Espagne</country><wicri:noRegion>Telematics Engineering Department, University of Vigo</wicri:noRegion></affiliation></author><author><name sortKey="Banugondi, Pavan" sort="Banugondi, Pavan" uniqKey="Banugondi P" first="Pavan" last="Banugondi">Pavan Banugondi</name><affiliation wicri:level="2"><inist:fA14 i1="02"><s1>Electrical & Computer Engineering Department, NC A&T State University</s1><s2>Greensboro, NC</s2><s3>USA</s3><sZ>2 aut.</sZ><sZ>3 aut.</sZ><sZ>7 aut.</sZ></inist:fA14><country>États-Unis</country><placeName><region type="state">Caroline du Nord</region></placeName></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">INIST</idno><idno type="inist">12-0306404</idno><date when="2010">2010</date><idno type="stanalyst">PASCAL 12-0306404 INIST</idno><idno type="RBID">Pascal:12-0306404</idno><idno type="wicri:Area/PascalFrancis/Corpus">000090</idno><idno type="wicri:Area/PascalFrancis/Curation">000682</idno><idno type="wicri:Area/PascalFrancis/Checkpoint">000166</idno><idno type="wicri:Area/Main/Merge">000797</idno><idno type="wicri:Area/Main/Curation">000792</idno><idno type="wicri:Area/Main/Exploration">000792</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Color Clustering Text Extraction Algorithm for Mobile Phone Images</title><author><name sortKey="Canedo Rodriguez, Adrian" sort="Canedo Rodriguez, Adrian" uniqKey="Canedo Rodriguez A" first="Adrián" last="Canedo-Rodriguez">Adrián Canedo-Rodriguez</name><affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Telematics Engineering Department, University of Vigo</s1><s3>ESP</s3><sZ>1 aut.</sZ><sZ>6 aut.</sZ></inist:fA14><country>Espagne</country><wicri:noRegion>Telematics Engineering Department, University of Vigo</wicri:noRegion></affiliation></author><author><name sortKey="Jung Hyoun Kim" sort="Jung Hyoun Kim" uniqKey="Jung Hyoun Kim" last="Jung Hyoun Kim">JUNG HYOUN KIM</name><affiliation wicri:level="2"><inist:fA14 i1="02"><s1>Electrical & Computer Engineering Department, NC A&T State University</s1><s2>Greensboro, NC</s2><s3>USA</s3><sZ>2 aut.</sZ><sZ>3 aut.</sZ><sZ>7 aut.</sZ></inist:fA14><country>États-Unis</country><placeName><region type="state">Caroline du Nord</region></placeName></affiliation></author><author><name sortKey="Kelly, John" sort="Kelly, John" uniqKey="Kelly J" first="John" last="Kelly">John Kelly</name><affiliation wicri:level="2"><inist:fA14 i1="02"><s1>Electrical & Computer Engineering Department, NC A&T State University</s1><s2>Greensboro, NC</s2><s3>USA</s3><sZ>2 aut.</sZ><sZ>3 aut.</sZ><sZ>7 aut.</sZ></inist:fA14><country>États-Unis</country><placeName><region type="state">Caroline du Nord</region></placeName></affiliation></author><author><name sortKey="Jung Hee Kim" sort="Jung Hee Kim" uniqKey="Jung Hee Kim" last="Jung Hee Kim">JUNG HEE KIM</name><affiliation wicri:level="2"><inist:fA14 i1="03"><s1>Computer Science Department, NC A&T State University</s1><s2>Greensboro, NC</s2><s3>USA</s3><sZ>4 aut.</sZ></inist:fA14><country>États-Unis</country><placeName><region type="state">Caroline du Nord</region></placeName></affiliation></author><author><name sortKey="Kim, Soo Hyung" sort="Kim, Soo Hyung" uniqKey="Kim S" first="Soo-Hyung" last="Kim">Soo-Hyung Kim</name><affiliation wicri:level="1"><inist:fA14 i1="04"><s1>Computer Science Department, Chonnam National University</s1><s3>KOR</s3><sZ>5 aut.</sZ></inist:fA14><country>Corée du Sud</country><wicri:noRegion>Computer Science Department, Chonnam National University</wicri:noRegion></affiliation></author><author><name sortKey="Blanco Fernindez, Yolanda" sort="Blanco Fernindez, Yolanda" uniqKey="Blanco Fernindez Y" first="Yolanda" last="Blanco-Fernindez">Yolanda Blanco-Fernindez</name><affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Telematics Engineering Department, University of Vigo</s1><s3>ESP</s3><sZ>1 aut.</sZ><sZ>6 aut.</sZ></inist:fA14><country>Espagne</country><wicri:noRegion>Telematics Engineering Department, University of Vigo</wicri:noRegion></affiliation></author><author><name sortKey="Banugondi, Pavan" sort="Banugondi, Pavan" uniqKey="Banugondi P" first="Pavan" last="Banugondi">Pavan Banugondi</name><affiliation wicri:level="2"><inist:fA14 i1="02"><s1>Electrical & Computer Engineering Department, NC A&T State University</s1><s2>Greensboro, NC</s2><s3>USA</s3><sZ>2 aut.</sZ><sZ>3 aut.</sZ><sZ>7 aut.</sZ></inist:fA14><country>États-Unis</country><placeName><region type="state">Caroline du Nord</region></placeName></affiliation></author></analytic></biblStruct></sourceDesc></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Character recognition</term><term>Cluster analysis</term><term>Color image</term><term>Commercial use</term><term>Illumination</term><term>Image databank</term><term>Information extraction</term><term>Luminance</term><term>Mobile phone</term><term>Natural scenes</term><term>Optical character recognition</term><term>Pattern extraction</term><term>Principal component analysis</term><term>Text</term><term>Video signal</term><term>blurring image</term></keywords><keywords scheme="Pascal" xml:lang="fr"><term>Texte</term><term>Extraction information</term><term>Signal vidéo</term><term>Banque image</term><term>Image couleur</term><term>Reconnaissance caractère</term><term>Reconnaissance optique caractère</term><term>Eclairement</term><term>Floutage</term><term>Téléphone portable</term><term>Intérêt commercial</term><term>Luminance</term><term>Analyse amas</term><term>Extraction forme</term><term>Analyse composante principale</term><term>Scène naturelle</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">Variety of approaches for text information extraction from images or video clips have been proposed so far, but none of them is suitable to be implemented over a low computational device, either because of their low accuracy, or slow performance. In this scenario, we propose a Text Extraction algorithm that extracts the text data within natural scene images taken with mobile phone, fast and accurately. The algorithm uses very efficient computations to calculate the Principal Color Components of a quantized image, and separates the main foreground-background colors, after which it extracts the text on the image. We have compared our algorithm with the Otsu algorithm by the use of a commercial OCR, achieving accuracy rates 12% higher, and performing 2 times faster than those algorithms. The proposed approach will be robust against common degradations, such as uneven illumination, or blurring. Therefore, this will be a very attractive algorithm that accurately separates foreground and background from scene text images and works effciently over low computational resources devices.</div></front></TEI><affiliations><list><country><li>Corée du Sud</li><li>Espagne</li><li>États-Unis</li></country><region><li>Caroline du Nord</li></region></list><tree><country name="Espagne"><noRegion><name sortKey="Canedo Rodriguez, Adrian" sort="Canedo Rodriguez, Adrian" uniqKey="Canedo Rodriguez A" first="Adrián" last="Canedo-Rodriguez">Adrián Canedo-Rodriguez</name></noRegion><name sortKey="Blanco Fernindez, Yolanda" sort="Blanco Fernindez, Yolanda" uniqKey="Blanco Fernindez Y" first="Yolanda" last="Blanco-Fernindez">Yolanda Blanco-Fernindez</name></country><country name="États-Unis"><region name="Caroline du Nord"><name sortKey="Jung Hyoun Kim" sort="Jung Hyoun Kim" uniqKey="Jung Hyoun Kim" last="Jung Hyoun Kim">JUNG HYOUN KIM</name></region><name sortKey="Banugondi, Pavan" sort="Banugondi, Pavan" uniqKey="Banugondi P" first="Pavan" last="Banugondi">Pavan Banugondi</name><name sortKey="Jung Hee Kim" sort="Jung Hee Kim" uniqKey="Jung Hee Kim" last="Jung Hee Kim">JUNG HEE KIM</name><name sortKey="Kelly, John" sort="Kelly, John" uniqKey="Kelly J" first="John" last="Kelly">John Kelly</name></country><country name="Corée du Sud"><noRegion><name sortKey="Kim, Soo Hyung" sort="Kim, Soo Hyung" uniqKey="Kim S" first="Soo-Hyung" last="Kim">Soo-Hyung Kim</name></noRegion></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 000792 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000792 | 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:12-0306404
|texte= Color Clustering Text Extraction Algorithm for Mobile Phone Images
}}
| This area was generated with Dilib version V0.6.32. |  |