Neural network-based text location in color images
Identifieur interne : 000C24 ( Istex/Corpus ); précédent : 000C23; suivant : 000C25Neural network-based text location in color images
Auteurs : Keechul JungSource :
- Pattern Recognition Letters [ 0167-8655 ] ; 2000.
Abstract
This paper proposes neural network-based text locations in complex color images. Texture information extracted on several color bands using neural networks is combined and corresponding text location algorithms are then developed. Text extraction filters can be automatically constructed using neural networks. Comparisons with other text location methods are presented; indicating that the proposed system has a better accuracy.
Url:
DOI: 10.1016/S0167-8655(01)00096-4
Links to Exploration step
ISTEX:D9842748AAD8B26A299A52ADA1B43F36FC03FFFCLe document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title>Neural network-based text location in color images</title><author><name sortKey="Jung, Keechul" sort="Jung, Keechul" uniqKey="Jung K" first="Keechul" last="Jung">Keechul Jung</name><affiliation><mods:affiliation>Computer Graphics Lab., School of Elect. and Comp. Eng., Sung Kyun Kwan University, Chunchun-dong, Jangan-gu, Suwon, Kyunggi-do 440-746, South Korea</mods:affiliation></affiliation><affiliation><mods:affiliation>E-mail: kjung@ece.skku.ac.kr</mods:affiliation></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:D9842748AAD8B26A299A52ADA1B43F36FC03FFFC</idno><date when="2001" year="2001">2001</date><idno type="doi">10.1016/S0167-8655(01)00096-4</idno><idno type="url">https://api.istex.fr/document/D9842748AAD8B26A299A52ADA1B43F36FC03FFFC/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">000C24</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a">Neural network-based text location in color images</title><author><name sortKey="Jung, Keechul" sort="Jung, Keechul" uniqKey="Jung K" first="Keechul" last="Jung">Keechul Jung</name><affiliation><mods:affiliation>Computer Graphics Lab., School of Elect. and Comp. Eng., Sung Kyun Kwan University, Chunchun-dong, Jangan-gu, Suwon, Kyunggi-do 440-746, South Korea</mods:affiliation></affiliation><affiliation><mods:affiliation>E-mail: kjung@ece.skku.ac.kr</mods:affiliation></affiliation></author></analytic><monogr></monogr><series><title level="j">Pattern Recognition Letters</title><title level="j" type="abbrev">PATREC</title><idno type="ISSN">0167-8655</idno><imprint><publisher>ELSEVIER</publisher><date type="published" when="2000">2000</date><biblScope unit="volume">22</biblScope><biblScope unit="issue">14</biblScope><biblScope unit="page" from="1503">1503</biblScope><biblScope unit="page" to="1515">1515</biblScope></imprint><idno type="ISSN">0167-8655</idno></series><idno type="istex">D9842748AAD8B26A299A52ADA1B43F36FC03FFFC</idno><idno type="DOI">10.1016/S0167-8655(01)00096-4</idno><idno type="PII">S0167-8655(01)00096-4</idno></biblStruct></sourceDesc><seriesStmt><idno type="ISSN">0167-8655</idno></seriesStmt></fileDesc><profileDesc><textClass></textClass><langUsage><language ident="en">en</language></langUsage></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">This paper proposes neural network-based text locations in complex color images. Texture information extracted on several color bands using neural networks is combined and corresponding text location algorithms are then developed. Text extraction filters can be automatically constructed using neural networks. Comparisons with other text location methods are presented; indicating that the proposed system has a better accuracy.</div></front></TEI><istex><corpusName>elsevier</corpusName><author><json:item><name>Keechul Jung</name><affiliations><json:string>Computer Graphics Lab., School of Elect. and Comp. Eng., Sung Kyun Kwan University, Chunchun-dong, Jangan-gu, Suwon, Kyunggi-do 440-746, South Korea</json:string><json:string>E-mail: kjung@ece.skku.ac.kr</json:string></affiliations></json:item></author><subject><json:item><lang><json:string>eng</json:string></lang><value>Text location</value></json:item><json:item><lang><json:string>eng</json:string></lang><value>Neural network</value></json:item><json:item><lang><json:string>eng</json:string></lang><value>Texture discrimination</value></json:item><json:item><lang><json:string>eng</json:string></lang><value>Arbitration on color bands</value></json:item><json:item><lang><json:string>eng</json:string></lang><value>Video indexing</value></json:item></subject><language><json:string>eng</json:string></language><abstract>This paper proposes neural network-based text locations in complex color images. Texture information extracted on several color bands using neural networks is combined and corresponding text location algorithms are then developed. Text extraction filters can be automatically constructed using neural networks. Comparisons with other text location methods are presented; indicating that the proposed system has a better accuracy.</abstract><qualityIndicators><score>4.974</score><pdfVersion>1.2</pdfVersion><pdfPageSize>544 x 743 pts</pdfPageSize><refBibsNative>true</refBibsNative><keywordCount>5</keywordCount><abstractCharCount>429</abstractCharCount><pdfWordCount>4278</pdfWordCount><pdfCharCount>25890</pdfCharCount><pdfPageCount>13</pdfPageCount><abstractWordCount>58</abstractWordCount></qualityIndicators><title>Neural network-based text location in color images</title><pii><json:string>S0167-8655(01)00096-4</json:string></pii><genre><json:string>brief communication</json:string></genre><host><volume>22</volume><pii><json:string>S0167-8655(00)X0080-3</json:string></pii><pages><last>1515</last><first>1503</first></pages><issn><json:string>0167-8655</json:string></issn><issue>14</issue><genre><json:string>Journal</json:string></genre><language><json:string>unknown</json:string></language><title>Pattern Recognition Letters</title><publicationDate>2001</publicationDate></host><categories><wos><json:string>COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE</json:string></wos></categories><publicationDate>2000</publicationDate><copyrightDate>2001</copyrightDate><doi><json:string>10.1016/S0167-8655(01)00096-4</json:string></doi><id>D9842748AAD8B26A299A52ADA1B43F36FC03FFFC</id><fulltext><json:item><original>true</original><mimetype>application/pdf</mimetype><extension>pdf</extension><uri>https://api.istex.fr/document/D9842748AAD8B26A299A52ADA1B43F36FC03FFFC/fulltext/pdf</uri></json:item><json:item><original>true</original><mimetype>text/plain</mimetype><extension>txt</extension><uri>https://api.istex.fr/document/D9842748AAD8B26A299A52ADA1B43F36FC03FFFC/fulltext/txt</uri></json:item><json:item><original>false</original><mimetype>application/zip</mimetype><extension>zip</extension><uri>https://api.istex.fr/document/D9842748AAD8B26A299A52ADA1B43F36FC03FFFC/fulltext/zip</uri></json:item><istex:fulltextTEI uri="https://api.istex.fr/document/D9842748AAD8B26A299A52ADA1B43F36FC03FFFC/fulltext/tei"><teiHeader><fileDesc><titleStmt><title level="a">Neural network-based text location in color images</title></titleStmt><publicationStmt><authority>ISTEX</authority><publisher>ELSEVIER</publisher><availability><p>ELSEVIER</p></availability><date>2001</date></publicationStmt><notesStmt><note type="content">Fig. 1: Frequency responses of text regions in red color band: (a) for text regions and (b) for non-text regions.</note><note type="content">Fig. 2: Color variation examples of horizontal lines of text regions in images.</note><note type="content">Fig. 3: Architecture of discrimination network that can arbitrate among multiple text detection networks.</note><note type="content">Fig. 4: Three-layer feed-forward neural network (Jain and Karu, 1996).</note><note type="content">Fig. 5: Behavior of the neural network: convergence of training errors according to feature sets used.</note><note type="content">Fig. 6: Sample outputs ((b)–(g)) of hidden nodes when applied to 128×128 image in (a).</note><note type="content">Fig. 7: Experimental results: (a) test images, (b) 3×3 window, and (c) 11×11 window.</note><note type="content">Fig. 8: Example of post-processing: (a) input image, (b) smoothed image, (c) horizontal projection profile, (d) text zone using vertical projection profile, and (e) final result.</note><note type="content">Fig. 9: Example of text location.</note><note type="content">Table 1: Recognition rates according to the threshold value</note><note type="content">Table 2: Mis-classification rates relative to input window size</note><note type="content">Table 3: Mis-classification rates according to network configuration</note><note type="content">Table 4: Detection rates according to arbitration method</note><note type="content">Table 5: Processing times for several routines</note><note type="content">Table 6: Experimental results</note><note type="content">Table 7: Comparison of classification rates using connected component method</note><note type="content">Table 8: Experimental results according to text size</note></notesStmt><sourceDesc><biblStruct type="inbook"><analytic><title level="a">Neural network-based text location in color images</title><author><persName><forename type="first">Keechul</forename><surname>Jung</surname></persName><email>kjung@ece.skku.ac.kr</email><note type="biography">Tel.: +82-331-290-7223; fax: +82-331-290-7211</note><affiliation>Tel.: +82-331-290-7223; fax: +82-331-290-7211</affiliation><affiliation>Computer Graphics Lab., School of Elect. and Comp. Eng., Sung Kyun Kwan University, Chunchun-dong, Jangan-gu, Suwon, Kyunggi-do 440-746, South Korea</affiliation></author></analytic><monogr><title level="j">Pattern Recognition Letters</title><title level="j" type="abbrev">PATREC</title><idno type="pISSN">0167-8655</idno><idno type="PII">S0167-8655(00)X0080-3</idno><imprint><publisher>ELSEVIER</publisher><date type="published" when="2000"></date><biblScope unit="volume">22</biblScope><biblScope unit="issue">14</biblScope><biblScope unit="page" from="1503">1503</biblScope><biblScope unit="page" to="1515">1515</biblScope></imprint></monogr><idno type="istex">D9842748AAD8B26A299A52ADA1B43F36FC03FFFC</idno><idno type="DOI">10.1016/S0167-8655(01)00096-4</idno><idno type="PII">S0167-8655(01)00096-4</idno></biblStruct></sourceDesc></fileDesc><profileDesc><creation><date>2001</date></creation><langUsage><language ident="en">en</language></langUsage><abstract xml:lang="en"><p>This paper proposes neural network-based text locations in complex color images. Texture information extracted on several color bands using neural networks is combined and corresponding text location algorithms are then developed. Text extraction filters can be automatically constructed using neural networks. Comparisons with other text location methods are presented; indicating that the proposed system has a better accuracy.</p></abstract><textClass><keywords scheme="keyword"><list><head>Keywords</head><item><term>Text location</term></item><item><term>Neural network</term></item><item><term>Texture discrimination</term></item><item><term>Arbitration on color bands</term></item><item><term>Video indexing</term></item></list></keywords></textClass></profileDesc><revisionDesc><change when="2000-06-26">Received</change><change when="2001-03-26">Modified</change><change when="2000">Published</change></revisionDesc></teiHeader></istex:fulltextTEI></fulltext><metadata><istex:metadataXml wicri:clean="Elsevier, elements deleted: ce:floats; body; tail"><istex:xmlDeclaration>version="1.0" encoding="utf-8"</istex:xmlDeclaration><istex:docType PUBLIC="-//ES//DTD journal article DTD version 4.5.2//EN//XML" URI="art452.dtd" name="istex:docType"><istex:entity SYSTEM="gr1" NDATA="IMAGE" name="gr1"></istex:entity><istex:entity SYSTEM="gr2" NDATA="IMAGE" name="gr2"></istex:entity><istex:entity SYSTEM="gr3" NDATA="IMAGE" name="gr3"></istex:entity><istex:entity SYSTEM="gr4" NDATA="IMAGE" name="gr4"></istex:entity><istex:entity SYSTEM="gr5" NDATA="IMAGE" name="gr5"></istex:entity><istex:entity SYSTEM="gr6" NDATA="IMAGE" name="gr6"></istex:entity><istex:entity SYSTEM="gr7" NDATA="IMAGE" name="gr7"></istex:entity><istex:entity SYSTEM="gr8" NDATA="IMAGE" name="gr8"></istex:entity><istex:entity SYSTEM="gr9" NDATA="IMAGE" name="gr9"></istex:entity></istex:docType><istex:document><converted-article version="4.5.2" docsubtype="sco"><item-info><jid>PATREC</jid><aid>2816</aid><ce:pii>S0167-8655(01)00096-4</ce:pii><ce:doi>10.1016/S0167-8655(01)00096-4</ce:doi><ce:copyright type="full-transfer" year="2001">Elsevier Science B.V.</ce:copyright></item-info><head><ce:title>Neural network-based text location in color images</ce:title><ce:author-group><ce:author><ce:given-name>Keechul</ce:given-name><ce:surname>Jung</ce:surname><ce:cross-ref refid="COR1"><ce:sup>∗</ce:sup></ce:cross-ref><ce:e-address type="email">kjung@ece.skku.ac.kr</ce:e-address></ce:author><ce:affiliation><ce:textfn>Computer Graphics Lab., School of Elect. and Comp. Eng., Sung Kyun Kwan University, Chunchun-dong, Jangan-gu, Suwon, Kyunggi-do 440-746, South Korea</ce:textfn></ce:affiliation><ce:correspondence id="COR1"><ce:label>∗</ce:label><ce:text>Tel.: +82-331-290-7223; fax: +82-331-290-7211</ce:text></ce:correspondence></ce:author-group><ce:date-received day="26" month="6" year="2000"></ce:date-received><ce:date-revised day="26" month="3" year="2001"></ce:date-revised><ce:abstract><ce:section-title>Abstract</ce:section-title><ce:abstract-sec><ce:simple-para>This paper proposes neural network-based text locations in complex color images. Texture information extracted on several color bands using neural networks is combined and corresponding text location algorithms are then developed. Text extraction filters can be automatically constructed using neural networks. Comparisons with other text location methods are presented; indicating that the proposed system has a better accuracy.</ce:simple-para></ce:abstract-sec></ce:abstract><ce:keywords class="keyword"><ce:section-title>Keywords</ce:section-title><ce:keyword><ce:text>Text location</ce:text></ce:keyword><ce:keyword><ce:text>Neural network</ce:text></ce:keyword><ce:keyword><ce:text>Texture discrimination</ce:text></ce:keyword><ce:keyword><ce:text>Arbitration on color bands</ce:text></ce:keyword><ce:keyword><ce:text>Video indexing</ce:text></ce:keyword></ce:keywords></head></converted-article></istex:document></istex:metadataXml><mods version="3.6"><titleInfo><title>Neural network-based text location in color images</title></titleInfo><titleInfo type="alternative" contentType="CDATA"><title>Neural network-based text location in color images</title></titleInfo><name type="personal"><namePart type="given">Keechul</namePart><namePart type="family">Jung</namePart><affiliation>Computer Graphics Lab., School of Elect. and Comp. Eng., Sung Kyun Kwan University, Chunchun-dong, Jangan-gu, Suwon, Kyunggi-do 440-746, South Korea</affiliation><affiliation>E-mail: kjung@ece.skku.ac.kr</affiliation><description>Tel.: +82-331-290-7223; fax: +82-331-290-7211</description><role><roleTerm type="text">author</roleTerm></role></name><typeOfResource>text</typeOfResource><genre type="brief communication" displayLabel="Short communication"></genre><originInfo><publisher>ELSEVIER</publisher><dateIssued encoding="w3cdtf">2000</dateIssued><dateCaptured encoding="w3cdtf">2000-06-26</dateCaptured><dateModified encoding="w3cdtf">2001-03-26</dateModified><copyrightDate encoding="w3cdtf">2001</copyrightDate></originInfo><language><languageTerm type="code" authority="iso639-2b">eng</languageTerm><languageTerm type="code" authority="rfc3066">en</languageTerm></language><physicalDescription><internetMediaType>text/html</internetMediaType></physicalDescription><abstract lang="en">This paper proposes neural network-based text locations in complex color images. Texture information extracted on several color bands using neural networks is combined and corresponding text location algorithms are then developed. Text extraction filters can be automatically constructed using neural networks. Comparisons with other text location methods are presented; indicating that the proposed system has a better accuracy.</abstract><note type="content">Fig. 1: Frequency responses of text regions in red color band: (a) for text regions and (b) for non-text regions.</note><note type="content">Fig. 2: Color variation examples of horizontal lines of text regions in images.</note><note type="content">Fig. 3: Architecture of discrimination network that can arbitrate among multiple text detection networks.</note><note type="content">Fig. 4: Three-layer feed-forward neural network (Jain and Karu, 1996).</note><note type="content">Fig. 5: Behavior of the neural network: convergence of training errors according to feature sets used.</note><note type="content">Fig. 6: Sample outputs ((b)–(g)) of hidden nodes when applied to 128×128 image in (a).</note><note type="content">Fig. 7: Experimental results: (a) test images, (b) 3×3 window, and (c) 11×11 window.</note><note type="content">Fig. 8: Example of post-processing: (a) input image, (b) smoothed image, (c) horizontal projection profile, (d) text zone using vertical projection profile, and (e) final result.</note><note type="content">Fig. 9: Example of text location.</note><note type="content">Table 1: Recognition rates according to the threshold value</note><note type="content">Table 2: Mis-classification rates relative to input window size</note><note type="content">Table 3: Mis-classification rates according to network configuration</note><note type="content">Table 4: Detection rates according to arbitration method</note><note type="content">Table 5: Processing times for several routines</note><note type="content">Table 6: Experimental results</note><note type="content">Table 7: Comparison of classification rates using connected component method</note><note type="content">Table 8: Experimental results according to text size</note><subject><genre>Keywords</genre><topic>Text location</topic><topic>Neural network</topic><topic>Texture discrimination</topic><topic>Arbitration on color bands</topic><topic>Video indexing</topic></subject><relatedItem type="host"><titleInfo><title>Pattern Recognition Letters</title></titleInfo><titleInfo type="abbreviated"><title>PATREC</title></titleInfo><genre type="Journal">journal</genre><originInfo><dateIssued encoding="w3cdtf">200112</dateIssued></originInfo><identifier type="ISSN">0167-8655</identifier><identifier type="PII">S0167-8655(00)X0080-3</identifier><part><date>200112</date><detail type="volume"><number>22</number><caption>vol.</caption></detail><detail type="issue"><number>14</number><caption>no.</caption></detail><extent unit="issue pages"><start>1457</start><end>1582</end></extent><extent unit="pages"><start>1503</start><end>1515</end></extent></part></relatedItem><identifier type="istex">D9842748AAD8B26A299A52ADA1B43F36FC03FFFC</identifier><identifier type="DOI">10.1016/S0167-8655(01)00096-4</identifier><identifier type="PII">S0167-8655(01)00096-4</identifier><accessCondition type="use and reproduction" contentType="">© 2001Elsevier Science B.V.</accessCondition><recordInfo><recordContentSource>ELSEVIER</recordContentSource><recordOrigin>Elsevier Science B.V., ©2001</recordOrigin></recordInfo></mods></metadata><enrichments><istex:catWosTEI uri="https://api.istex.fr/document/D9842748AAD8B26A299A52ADA1B43F36FC03FFFC/enrichments/catWos"><teiHeader><profileDesc><textClass><classCode scheme="WOS">COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE</classCode></textClass></profileDesc></teiHeader></istex:catWosTEI></enrichments><serie></serie></istex></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/Istex/Corpus
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000C24 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Istex/Corpus/biblio.hfd -nk 000C24 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Ticri/CIDE
|area= OcrV1
|flux= Istex
|étape= Corpus
|type= RBID
|clé= ISTEX:D9842748AAD8B26A299A52ADA1B43F36FC03FFFC
|texte= Neural network-based text location in color images
}}
| This area was generated with Dilib version V0.6.32. |  |