Segmenting Texts From Outdoor Images Taken By Mobile Phones Using Color Features
Identifieur interne : 000543 ( Main/Exploration ); précédent : 000542; suivant : 000544Segmenting Texts From Outdoor Images Taken By Mobile Phones Using Color Features
Auteurs : ZONGYI LIU [États-Unis] ; HANNING ZHOU [États-Unis]Source :
- Proceedings of SPIE, the International Society for Optical Engineering [ 0277-786X ] ; 2011.
Descripteurs français
- Pascal (Inist)
English descriptors
- KwdEn :
Abstract
Recognizing texts from images taken by mobile phones with low resolution has wide applications. It has been shown that a good image binarization can substantially improve the performances of OCR engines. In this paper, we present a framework to segment texts from outdoor images taken by mobile phones using color features. The framework consists of three steps: (i) the initial process including image enhancement, binarization and noise filtering, where we binarize the input images in each RGB channel, and apply component level noise filtering; (ii) grouping components into blocks using color features, where we compute the component similarities by dynamically adjusting the weights of RGB channels, and merge groups hierachically, and (iii) blocks selection, where we use the run-length features and choose the Support Vector Machine (SVM) as the classifier. We tested the algorithm using 13 outdoor images taken by an old-style LG-64693 mobile phone with 640x480 resolution. We compared the segmentation results with Tsar's algorithm, a state-of-the-art camera text detection algorithm, and show that our algorithm is more robust, particularly in terms of the false alarm rates. In addition, we also evaluated the impacts of our algorithm on the Abbyy's FineReader, one of the most popular commercial OCR engines in the market.
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream PascalFrancis, to step Corpus: 000135
- to stream PascalFrancis, to step Curation: 000638
- to stream PascalFrancis, to step Checkpoint: 000097
- to stream Main, to step Merge: 000549
- to stream Main, to step Curation: 000543
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Segmenting Texts From Outdoor Images Taken By Mobile Phones Using Color Features</title><author><name sortKey="Zongyi Liu" sort="Zongyi Liu" uniqKey="Zongyi Liu" last="Zongyi Liu">ZONGYI LIU</name><affiliation wicri:level="2"><inist:fA14 i1="01"><s1>Amazon.com, Fifth Avenue Suite 1500</s1><s2>Seattle, WA 98104</s2><s3>USA</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ></inist:fA14><country>États-Unis</country><placeName><region type="state">Washington (État)</region></placeName></affiliation></author><author><name sortKey="Hanning Zhou" sort="Hanning Zhou" uniqKey="Hanning Zhou" last="Hanning Zhou">HANNING ZHOU</name><affiliation wicri:level="2"><inist:fA14 i1="01"><s1>Amazon.com, Fifth Avenue Suite 1500</s1><s2>Seattle, WA 98104</s2><s3>USA</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ></inist:fA14><country>États-Unis</country><placeName><region type="state">Washington (État)</region></placeName></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">INIST</idno><idno type="inist">11-0278997</idno><date when="2011">2011</date><idno type="stanalyst">PASCAL 11-0278997 INIST</idno><idno type="RBID">Pascal:11-0278997</idno><idno type="wicri:Area/PascalFrancis/Corpus">000135</idno><idno type="wicri:Area/PascalFrancis/Curation">000638</idno><idno type="wicri:Area/PascalFrancis/Checkpoint">000097</idno><idno type="wicri:doubleKey">0277-786X:2011:Zongyi Liu:segmenting:texts:from</idno><idno type="wicri:Area/Main/Merge">000549</idno><idno type="wicri:Area/Main/Curation">000543</idno><idno type="wicri:Area/Main/Exploration">000543</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Segmenting Texts From Outdoor Images Taken By Mobile Phones Using Color Features</title><author><name sortKey="Zongyi Liu" sort="Zongyi Liu" uniqKey="Zongyi Liu" last="Zongyi Liu">ZONGYI LIU</name><affiliation wicri:level="2"><inist:fA14 i1="01"><s1>Amazon.com, Fifth Avenue Suite 1500</s1><s2>Seattle, WA 98104</s2><s3>USA</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ></inist:fA14><country>États-Unis</country><placeName><region type="state">Washington (État)</region></placeName></affiliation></author><author><name sortKey="Hanning Zhou" sort="Hanning Zhou" uniqKey="Hanning Zhou" last="Hanning Zhou">HANNING ZHOU</name><affiliation wicri:level="2"><inist:fA14 i1="01"><s1>Amazon.com, Fifth Avenue Suite 1500</s1><s2>Seattle, WA 98104</s2><s3>USA</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ></inist:fA14><country>États-Unis</country><placeName><region type="state">Washington (État)</region></placeName></affiliation></author></analytic><series><title level="j" type="main">Proceedings of SPIE, the International Society for Optical Engineering</title><title level="j" type="abbreviated">Proc. SPIE Int. Soc. Opt. Eng.</title><idno type="ISSN">0277-786X</idno><imprint><date when="2011">2011</date></imprint></series></biblStruct></sourceDesc><seriesStmt><title level="j" type="main">Proceedings of SPIE, the International Society for Optical Engineering</title><title level="j" type="abbreviated">Proc. SPIE Int. Soc. Opt. Eng.</title><idno type="ISSN">0277-786X</idno></seriesStmt></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Algorithms</term><term>Binary image</term><term>Image enhancement</term><term>Image processing</term><term>Image quality</term><term>Imagery</term><term>Low resolution</term><term>Mobile handsets</term><term>Mobile radio</term><term>Optical character recognition</term><term>Outdoor installation</term><term>Performance evaluation</term><term>Segmentation</term></keywords><keywords scheme="Pascal" xml:lang="fr"><term>Traitement image</term><term>Radiocommunication service mobile</term><term>Imagerie</term><term>Algorithme</term><term>Evaluation performance</term><term>Segmentation</term><term>Installation extérieure</term><term>Téléphone portable</term><term>Basse résolution</term><term>Image binaire</term><term>Reconnaissance optique caractère</term><term>Accentuation image</term><term>Qualité image</term><term>0130C</term><term>4230</term><term>4230V</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">Recognizing texts from images taken by mobile phones with low resolution has wide applications. It has been shown that a good image binarization can substantially improve the performances of OCR engines. In this paper, we present a framework to segment texts from outdoor images taken by mobile phones using color features. The framework consists of three steps: (i) the initial process including image enhancement, binarization and noise filtering, where we binarize the input images in each RGB channel, and apply component level noise filtering; (ii) grouping components into blocks using color features, where we compute the component similarities by dynamically adjusting the weights of RGB channels, and merge groups hierachically, and (iii) blocks selection, where we use the run-length features and choose the Support Vector Machine (SVM) as the classifier. We tested the algorithm using 13 outdoor images taken by an old-style LG-64693 mobile phone with 640x480 resolution. We compared the segmentation results with Tsar's algorithm, a state-of-the-art camera text detection algorithm, and show that our algorithm is more robust, particularly in terms of the false alarm rates. In addition, we also evaluated the impacts of our algorithm on the Abbyy's FineReader, one of the most popular commercial OCR engines in the market.</div></front></TEI><affiliations><list><country><li>États-Unis</li></country><region><li>Washington (État)</li></region></list><tree><country name="États-Unis"><region name="Washington (État)"><name sortKey="Zongyi Liu" sort="Zongyi Liu" uniqKey="Zongyi Liu" last="Zongyi Liu">ZONGYI LIU</name></region><name sortKey="Hanning Zhou" sort="Hanning Zhou" uniqKey="Hanning Zhou" last="Hanning Zhou">HANNING ZHOU</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 000543 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000543 | 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:11-0278997
|texte= Segmenting Texts From Outdoor Images Taken By Mobile Phones Using Color Features
}}
| This area was generated with Dilib version V0.6.32. |  |