Extracting Meaningful Curves from Images
Identifieur interne : 000824 ( Istex/Corpus ); précédent : 000823; suivant : 000825Extracting Meaningful Curves from Images
Auteurs : Frédéric Cao ; José-Luis Lisani ; Jean-Michel Morel ; Pablo Musé ; Frédéric SurSource :
- Lecture Notes in Mathematics [ 0075-8434 ]
Abstract
The set of level lines of an image (isophotes) or topographic map is a complete and contrast invariant representation of an image. Level lines are ordered by inclusion in a tree structure. These two structure properties make level lines excellent candidates to shape representatives. However, some complexity issues have to be handled: The number of level lines in eight-bits encoded images of size 512×512 is typically 105. Most of them are very small lines due to noise or micro-texture. So the stable level lines must be selected, namely the ones that are likely to correspond to image contours. The starting point is the MSER method, a variant of the Monasse and Guichard Fast Level Set Transform. The MSER selects a set of level lines which are local extrema of contrast. This method will be put in the Helmholtz framework, following the a contrario boundary detection algorithm by Desolneux, Moisan and Morel [51], [54] and two powerful recent variants. The experiments in this chapter will show that selecting the most meaningful level lines reduces their number by a factor 100 without significant shape contents loss. A method which selects one out of hundred level lines in the image without significant information loss is necessarily sophisticated. Sect. 2.1 briefly reviews the level line tree of a digital image. Sect. 2.2 describes a first way to extract well contrasted level lines, the MSER method. Sect. 2.3 makes an account of the Desolneux et al. maximal meaningful boundaries and Sect. 2.4 gives a mathematical justification which was actually missing in the original theory. Sect. 2.5 is devoted to a multiscale extension which avoids missing boundaries because of high noise level and Sect. 2.6 deals with the so called “blue sky” effect which can lead to over-detections in textured parts of the image.
Url:
DOI: 10.1007/978-3-540-68481-7_2
Links to Exploration step
ISTEX:247E8CE7C3BBEAB502372C25E886D4F903F4A476Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Extracting Meaningful Curves from Images</title><author wicri:is="90%"><name sortKey="Cao, Frederic" sort="Cao, Frederic" uniqKey="Cao F" first="Frédéric" last="Cao">Frédéric Cao</name><affiliation><mods:affiliation>DxO Labs, 3 rue Nationale, 92100 Boulogne Billancourt, France</mods:affiliation></affiliation><affiliation><mods:affiliation>E-mail: fcao@dxo.com</mods:affiliation></affiliation></author><author wicri:is="90%"><name sortKey="Lisani, Jose Luis" sort="Lisani, Jose Luis" uniqKey="Lisani J" first="José-Luis" last="Lisani">José-Luis Lisani</name><affiliation><mods:affiliation>Dep. Matemàtiques i Informàtica, University Balearic Islands, ctra. Valldemossa km.7,5, 07122 Palma de Mallorca, Balears, Spain</mods:affiliation></affiliation><affiliation><mods:affiliation>E-mail: joseluis.lisani@uib.es</mods:affiliation></affiliation></author><author wicri:is="90%"><name sortKey="Morel, Jean Michel" sort="Morel, Jean Michel" uniqKey="Morel J" first="Jean-Michel" last="Morel">Jean-Michel Morel</name><affiliation><mods:affiliation>Ecole Normale Supérieure de Cachan, CMLA, 61 av. du Président Wilson, 94235 Cachan Cédex, France</mods:affiliation></affiliation><affiliation><mods:affiliation>E-mail: morel@cmla.ens-cachan.fr</mods:affiliation></affiliation></author><author wicri:is="90%"><name sortKey="Muse, Pablo" sort="Muse, Pablo" uniqKey="Muse P" first="Pablo" last="Musé">Pablo Musé</name><affiliation><mods:affiliation>Instituto de Ingeniería Eléctrica, Julio Herrera y Reissig 565, 11300 Montevideo, Uruguay</mods:affiliation></affiliation><affiliation><mods:affiliation>E-mail: pmuse@fing.edu.uy</mods:affiliation></affiliation></author><author wicri:is="90%"><name sortKey="Sur, Frederic" sort="Sur, Frederic" uniqKey="Sur F" first="Frédéric" last="Sur">Frédéric Sur</name><affiliation><mods:affiliation>Loria Bat. C - projet Magrit Campus Scientifique, 54506 Vandoeuvre-lès-Nancy Cédex, BP 239, France</mods:affiliation></affiliation><affiliation><mods:affiliation>E-mail: sur@loria.fr</mods:affiliation></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:247E8CE7C3BBEAB502372C25E886D4F903F4A476</idno><date when="2008" year="2008">2008</date><idno type="doi">10.1007/978-3-540-68481-7_2</idno><idno type="url">https://api.istex.fr/ark:/67375/HCB-M2WBVBBM-9/fulltext.pdf</idno><idno type="wicri:Area/Istex/Corpus">000824</idno><idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Corpus" wicri:corpus="ISTEX">000824</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Extracting Meaningful Curves from Images</title><author wicri:is="90%"><name sortKey="Cao, Frederic" sort="Cao, Frederic" uniqKey="Cao F" first="Frédéric" last="Cao">Frédéric Cao</name><affiliation><mods:affiliation>DxO Labs, 3 rue Nationale, 92100 Boulogne Billancourt, France</mods:affiliation></affiliation><affiliation><mods:affiliation>E-mail: fcao@dxo.com</mods:affiliation></affiliation></author><author wicri:is="90%"><name sortKey="Lisani, Jose Luis" sort="Lisani, Jose Luis" uniqKey="Lisani J" first="José-Luis" last="Lisani">José-Luis Lisani</name><affiliation><mods:affiliation>Dep. Matemàtiques i Informàtica, University Balearic Islands, ctra. Valldemossa km.7,5, 07122 Palma de Mallorca, Balears, Spain</mods:affiliation></affiliation><affiliation><mods:affiliation>E-mail: joseluis.lisani@uib.es</mods:affiliation></affiliation></author><author wicri:is="90%"><name sortKey="Morel, Jean Michel" sort="Morel, Jean Michel" uniqKey="Morel J" first="Jean-Michel" last="Morel">Jean-Michel Morel</name><affiliation><mods:affiliation>Ecole Normale Supérieure de Cachan, CMLA, 61 av. du Président Wilson, 94235 Cachan Cédex, France</mods:affiliation></affiliation><affiliation><mods:affiliation>E-mail: morel@cmla.ens-cachan.fr</mods:affiliation></affiliation></author><author wicri:is="90%"><name sortKey="Muse, Pablo" sort="Muse, Pablo" uniqKey="Muse P" first="Pablo" last="Musé">Pablo Musé</name><affiliation><mods:affiliation>Instituto de Ingeniería Eléctrica, Julio Herrera y Reissig 565, 11300 Montevideo, Uruguay</mods:affiliation></affiliation><affiliation><mods:affiliation>E-mail: pmuse@fing.edu.uy</mods:affiliation></affiliation></author><author wicri:is="90%"><name sortKey="Sur, Frederic" sort="Sur, Frederic" uniqKey="Sur F" first="Frédéric" last="Sur">Frédéric Sur</name><affiliation><mods:affiliation>Loria Bat. C - projet Magrit Campus Scientifique, 54506 Vandoeuvre-lès-Nancy Cédex, BP 239, France</mods:affiliation></affiliation><affiliation><mods:affiliation>E-mail: sur@loria.fr</mods:affiliation></affiliation></author></analytic><monogr></monogr><series><title level="s" type="main" xml:lang="en">Lecture Notes in Mathematics</title><idno type="ISSN">0075-8434</idno><idno type="ISSN">0075-8434</idno></series></biblStruct></sourceDesc><seriesStmt><idno type="ISSN">0075-8434</idno></seriesStmt></fileDesc><profileDesc><textClass></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">The set of level lines of an image (isophotes) or topographic map is a complete and contrast invariant representation of an image. Level lines are ordered by inclusion in a tree structure. These two structure properties make level lines excellent candidates to shape representatives. However, some complexity issues have to be handled: The number of level lines in eight-bits encoded images of size 512×512 is typically 105. Most of them are very small lines due to noise or micro-texture. So the stable level lines must be selected, namely the ones that are likely to correspond to image contours. The starting point is the MSER method, a variant of the Monasse and Guichard Fast Level Set Transform. The MSER selects a set of level lines which are local extrema of contrast. This method will be put in the Helmholtz framework, following the a contrario boundary detection algorithm by Desolneux, Moisan and Morel [51], [54] and two powerful recent variants. The experiments in this chapter will show that selecting the most meaningful level lines reduces their number by a factor 100 without significant shape contents loss. A method which selects one out of hundred level lines in the image without significant information loss is necessarily sophisticated. Sect. 2.1 briefly reviews the level line tree of a digital image. Sect. 2.2 describes a first way to extract well contrasted level lines, the MSER method. Sect. 2.3 makes an account of the Desolneux et al. maximal meaningful boundaries and Sect. 2.4 gives a mathematical justification which was actually missing in the original theory. Sect. 2.5 is devoted to a multiscale extension which avoids missing boundaries because of high noise level and Sect. 2.6 deals with the so called “blue sky” effect which can lead to over-detections in textured parts of the image.</div></front></TEI><istex><corpusName>springer-ebooks</corpusName><author><json:item><name>Frédéric Cao</name><affiliations><json:string>DxO Labs, 3 rue Nationale, 92100 Boulogne Billancourt, France</json:string><json:string>E-mail: fcao@dxo.com</json:string></affiliations></json:item><json:item><name>José-Luis Lisani</name><affiliations><json:string>Dep. Matemàtiques i Informàtica, University Balearic Islands, ctra. Valldemossa km.7,5, 07122 Palma de Mallorca, Balears, Spain</json:string><json:string>E-mail: joseluis.lisani@uib.es</json:string></affiliations></json:item><json:item><name>Jean-Michel Morel</name><affiliations><json:string>Ecole Normale Supérieure de Cachan, CMLA, 61 av. du Président Wilson, 94235 Cachan Cédex, France</json:string><json:string>E-mail: morel@cmla.ens-cachan.fr</json:string></affiliations></json:item><json:item><name>Pablo Musé</name><affiliations><json:string>Instituto de Ingeniería Eléctrica, Julio Herrera y Reissig 565, 11300 Montevideo, Uruguay</json:string><json:string>E-mail: pmuse@fing.edu.uy</json:string></affiliations></json:item><json:item><name>Frédéric Sur</name><affiliations><json:string>Loria Bat. C - projet Magrit Campus Scientifique, 54506 Vandoeuvre-lès-Nancy Cédex, BP 239, France</json:string><json:string>E-mail: sur@loria.fr</json:string></affiliations></json:item></author><arkIstex>ark:/67375/HCB-M2WBVBBM-9</arkIstex><language><json:string>eng</json:string></language><originalGenre><json:string>OriginalPaper</json:string></originalGenre><abstract>The set of level lines of an image (isophotes) or topographic map is a complete and contrast invariant representation of an image. Level lines are ordered by inclusion in a tree structure. These two structure properties make level lines excellent candidates to shape representatives. However, some complexity issues have to be handled: The number of level lines in eight-bits encoded images of size 512×512 is typically 105. Most of them are very small lines due to noise or micro-texture. So the stable level lines must be selected, namely the ones that are likely to correspond to image contours. The starting point is the MSER method, a variant of the Monasse and Guichard Fast Level Set Transform. The MSER selects a set of level lines which are local extrema of contrast. This method will be put in the Helmholtz framework, following the a contrario boundary detection algorithm by Desolneux, Moisan and Morel [51], [54] and two powerful recent variants. The experiments in this chapter will show that selecting the most meaningful level lines reduces their number by a factor 100 without significant shape contents loss. A method which selects one out of hundred level lines in the image without significant information loss is necessarily sophisticated. Sect. 2.1 briefly reviews the level line tree of a digital image. Sect. 2.2 describes a first way to extract well contrasted level lines, the MSER method. Sect. 2.3 makes an account of the Desolneux et al. maximal meaningful boundaries and Sect. 2.4 gives a mathematical justification which was actually missing in the original theory. Sect. 2.5 is devoted to a multiscale extension which avoids missing boundaries because of high noise level and Sect. 2.6 deals with the so called “blue sky” effect which can lead to over-detections in textured parts of the image.</abstract><qualityIndicators><score>10</score><pdfWordCount>7331</pdfWordCount><pdfCharCount>37639</pdfCharCount><pdfVersion>1.3</pdfVersion><pdfPageCount>21</pdfPageCount><pdfPageSize>439.37 x 666.142 pts</pdfPageSize><refBibsNative>false</refBibsNative><abstractWordCount>298</abstractWordCount><abstractCharCount>1826</abstractCharCount><keywordCount>0</keywordCount></qualityIndicators><title>Extracting Meaningful Curves from Images</title><chapterId><json:string>2</json:string><json:string>Chap2</json:string></chapterId><genre><json:string>research-article</json:string></genre><serie><title>Lecture Notes in Mathematics</title><language><json:string>unknown</json:string></language><copyrightDate>2008</copyrightDate><issn><json:string>0075-8434</json:string></issn><volume>I</volume><editor><json:item><name>J. -M. Morel</name><affiliations><json:string>Cachan</json:string></affiliations></json:item><json:item><name>F. Takens</name><affiliations><json:string>Groningen</json:string></affiliations></json:item><json:item><name>B. Teissier</name><affiliations><json:string>Paris</json:string></affiliations></json:item></editor></serie><host><title>A Theory of Shape Identification</title><language><json:string>unknown</json:string></language><copyrightDate>2008</copyrightDate><doi><json:string>10.1007/978-3-540-68481-7</json:string></doi><issn><json:string>0075-8434</json:string></issn><eisbn><json:string>978-3-540-68481-7</json:string></eisbn><bookId><json:string>978-3-540-68481-7</json:string></bookId><isbn><json:string>978-3-540-68480-0</json:string></isbn><volume>1948</volume><pages><first>15</first><last>35</last></pages><genre><json:string>book-series</json:string></genre><author><json:item><name>Frédéric Cao</name><affiliations><json:string>DxO Labs, 3 rue Nationale, 92100 Boulogne Billancourt, France</json:string><json:string>E-mail: fcao@dxo.com</json:string></affiliations></json:item><json:item><name>José-Luis Lisani</name><affiliations><json:string>Dep. Matemàtiques i Informàtica, University Balearic Islands, ctra. Valldemossa km.7,5, 07122 Palma de Mallorca, Balears, Spain</json:string><json:string>E-mail: joseluis.lisani@uib.es</json:string></affiliations></json:item><json:item><name>Jean-Michel Morel</name><affiliations><json:string>Ecole Normale Supérieure de Cachan, CMLA, 61 av. du Président Wilson, 94235 Cachan Cédex, France</json:string><json:string>E-mail: morel@cmla.ens-cachan.fr</json:string></affiliations></json:item><json:item><name>Pablo Musé</name><affiliations><json:string>Instituto de Ingeniería Eléctrica, Julio Herrera y Reissig 565, 11300 Montevideo, Uruguay</json:string><json:string>E-mail: pmuse@fing.edu.uy</json:string></affiliations></json:item><json:item><name>Frédéric Sur</name><affiliations><json:string>Loria Bat. C - projet Magrit Campus Scientifique, 54506 Vandoeuvre-lès-Nancy Cédex, BP 239, France</json:string><json:string>E-mail: sur@loria.fr</json:string></affiliations></json:item></author><subject><json:item><value>Mathematics and Statistics</value></json:item><json:item><value>Mathematics</value></json:item><json:item><value>Geometry</value></json:item><json:item><value>Visualization</value></json:item><json:item><value>Image Processing and Computer Vision</value></json:item><json:item><value>Artificial Intelligence (incl. Robotics)</value></json:item><json:item><value>Computer Imaging, Vision, Pattern Recognition and Graphics</value></json:item><json:item><value>Game Theory, Economics, Social and Behav. Sciences</value></json:item></subject></host><ark><json:string>ark:/67375/HCB-M2WBVBBM-9</json:string></ark><publicationDate>2008</publicationDate><copyrightDate>2008</copyrightDate><doi><json:string>10.1007/978-3-540-68481-7_2</json:string></doi><id>247E8CE7C3BBEAB502372C25E886D4F903F4A476</id><score>1</score><fulltext><json:item><extension>pdf</extension><original>true</original><mimetype>application/pdf</mimetype><uri>https://api.istex.fr/ark:/67375/HCB-M2WBVBBM-9/fulltext.pdf</uri></json:item><json:item><extension>zip</extension><original>false</original><mimetype>application/zip</mimetype><uri>https://api.istex.fr/ark:/67375/HCB-M2WBVBBM-9/bundle.zip</uri></json:item><istex:fulltextTEI uri="https://api.istex.fr/ark:/67375/HCB-M2WBVBBM-9/fulltext.tei"><teiHeader><fileDesc><titleStmt><title level="a" type="main" xml:lang="en">Extracting Meaningful Curves from Images</title></titleStmt><publicationStmt><authority>ISTEX</authority><availability><licence>Springer-Verlag Berlin Heidelberg</licence></availability><date when="2008">2008</date></publicationStmt><notesStmt><note type="content-type" subtype="research-article" source="OriginalPaper" scheme="https://content-type.data.istex.fr/ark:/67375/XTP-1JC4F85T-7">research-article</note><note type="publication-type" subtype="book-series" scheme="https://publication-type.data.istex.fr/ark:/67375/JMC-0G6R5W5T-Z">book-series</note></notesStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Extracting Meaningful Curves from Images</title><idno type="istex">247E8CE7C3BBEAB502372C25E886D4F903F4A476</idno><idno type="ark">ark:/67375/HCB-M2WBVBBM-9</idno><idno type="DOI">10.1007/978-3-540-68481-7_2</idno></analytic><monogr><title level="m" type="main">A Theory of Shape Identification</title><title level="m" type="part">Extracting Image boundaries</title><idno type="DOI">10.1007/978-3-540-68481-7</idno><idno type="book-id">978-3-540-68481-7</idno><idno type="ISBN">978-3-540-68480-0</idno><idno type="eISBN">978-3-540-68481-7</idno><idno type="chapter-id">Chap2</idno><idno type="part-id">Part1</idno><author><persName><forename type="first">Frédéric</forename><surname>Cao</surname></persName><email>fcao@dxo.com</email><affiliation><orgName type="institution">DxO Labs</orgName><address><street>3 rue Nationale</street><postCode>92100 Boulogne Billancourt</postCode><country key="FR">FRANCE</country></address></affiliation></author><author><persName><forename type="first">José-Luis</forename><surname>Lisani</surname></persName><email>joseluis.lisani@uib.es</email><affiliation><orgName type="department">Dep. Matemàtiques i Informàtica</orgName><orgName type="institution">University Balearic Islands</orgName><address><street>ctra. Valldemossa km.7,5</street><settlement>Balears</settlement><postCode>07122 Palma de Mallorca</postCode><country key="ES">SPAIN</country></address></affiliation></author><author><persName><forename type="first">Jean-Michel</forename><surname>Morel</surname></persName><email>morel@cmla.ens-cachan.fr</email><affiliation><orgName type="department">Ecole Normale Supérieure de Cachan</orgName><orgName type="institution">CMLA</orgName><address><street>61 av. du Président Wilson</street><postCode>94235 Cachan Cédex</postCode><country key="FR">FRANCE</country></address></affiliation></author><author><persName><forename type="first">Pablo</forename><surname>Musé</surname></persName><email>pmuse@fing.edu.uy</email><affiliation><orgName type="institution">Instituto de Ingeniería Eléctrica</orgName><address><street>Julio Herrera y Reissig 565</street><postCode>11300 Montevideo</postCode><country key="UY">URUGUAY</country></address></affiliation></author><author><persName><forename type="first">Frédéric</forename><surname>Sur</surname></persName><email>sur@loria.fr</email><affiliation><orgName type="institution">Loria Bat. C - projet Magrit Campus Scientifique</orgName><address><street>54506 Vandoeuvre-lès-Nancy Cédex</street><postCode>BP 239</postCode><country key="FR">FRANCE</country></address></affiliation></author><imprint><biblScope unit="vol">1948</biblScope><biblScope unit="page" from="15">15</biblScope><biblScope unit="page" to="35">35</biblScope><biblScope unit="chapter-count">11</biblScope><biblScope unit="part-chapter-count">2</biblScope></imprint></monogr><series><title level="s" type="main" xml:lang="en">Lecture Notes in Mathematics</title><editor><persName><forename type="first">J.</forename><forename type="first">-M.</forename><surname>Morel</surname></persName><affiliation><address><country key=""></country></address></affiliation></editor><editor><persName><forename type="first">F.</forename><surname>Takens</surname></persName><affiliation><address><country key=""></country></address></affiliation></editor><editor><persName><forename type="first">B.</forename><surname>Teissier</surname></persName><affiliation><address><country key=""></country></address></affiliation></editor><idno type="pISSN">0075-8434</idno><idno type="seriesID">304</idno></series></biblStruct></sourceDesc></fileDesc><profileDesc><abstract xml:lang="en"><p>The set of level lines of an image (isophotes) or topographic map is a complete and contrast invariant representation of an image. Level lines are ordered by inclusion in a tree structure. These two structure properties make level lines excellent candidates to shape representatives. However, some complexity issues have to be handled: The number of level lines in eight-bits encoded images of size 512×512 is typically 10<hi rend="superscript">5</hi>. Most of them are very small lines due to noise or micro-texture. So the stable level lines must be selected, namely the ones that are likely to correspond to image contours. The starting point is the MSER method, a variant of the Monasse and Guichard Fast Level Set Transform. The MSER selects a set of level lines which are local extrema of contrast. This method will be put in the Helmholtz framework, following the <hi rend="italic">a contrario</hi> boundary detection algorithm by Desolneux, Moisan and Morel [51], [54] and two powerful recent variants. The experiments in this chapter will show that selecting the most meaningful level lines reduces their number by a factor 100 without significant shape contents loss.</p><p>A method which selects one out of hundred level lines in the image without significant information loss is necessarily sophisticated. Sect. 2.1 briefly reviews the level line tree of a digital image. Sect. 2.2 describes a first way to extract well contrasted level lines, the MSER method. Sect. 2.3 makes an account of the Desolneux et al. maximal meaningful boundaries and Sect. 2.4 gives a mathematical justification which was actually missing in the original theory. Sect. 2.5 is devoted to a multiscale extension which avoids missing boundaries because of high noise level and Sect. 2.6 deals with the so called “blue sky” effect which can lead to over-detections in textured parts of the image.</p></abstract><textClass ana="subject"><keywords scheme="book-subject-collection"><list><label>SUCO11649</label><item><term>Mathematics and Statistics</term></item></list></keywords></textClass><textClass ana="subject"><keywords scheme="book-subject"><list><label>SCM</label><item><term type="Primary">Mathematics</term></item><label>SCM21006</label><item><term type="Secondary" subtype="priority-1">Geometry</term></item><label>SCM14034</label><item><term type="Secondary" subtype="priority-2">Visualization</term></item><label>SCI22021</label><item><term type="Secondary" subtype="priority-3">Image Processing and Computer Vision</term></item><label>SCI21017</label><item><term type="Secondary" subtype="priority-4">Artificial Intelligence (incl. Robotics)</term></item><label>SCI22005</label><item><term type="Secondary" subtype="priority-5">Computer Imaging, Vision, Pattern Recognition and Graphics</term></item><label>SCM13011</label><item><term type="Secondary" subtype="priority-6">Game Theory, Economics, Social and Behav. Sciences</term></item></list></keywords></textClass><langUsage><language ident="EN"></language></langUsage></profileDesc></teiHeader></istex:fulltextTEI><json:item><extension>txt</extension><original>false</original><mimetype>text/plain</mimetype><uri>https://api.istex.fr/ark:/67375/HCB-M2WBVBBM-9/fulltext.txt</uri></json:item></fulltext><metadata><istex:metadataXml wicri:clean="corpus springer-ebooks not found" wicri:toSee="no header"><istex:xmlDeclaration>version="1.0" encoding="UTF-8"</istex:xmlDeclaration><istex:docType PUBLIC="-//Springer-Verlag//DTD A++ V2.4//EN" URI="http://devel.springer.de/A++/V2.4/DTD/A++V2.4.dtd" name="istex:docType"></istex:docType><istex:document><Publisher><PublisherInfo><PublisherName>Springer Berlin Heidelberg</PublisherName><PublisherLocation>Berlin, Heidelberg</PublisherLocation></PublisherInfo><Series><SeriesInfo SeriesType="Series" TocLevels="0"><SeriesID>304</SeriesID><SeriesPrintISSN>0075-8434</SeriesPrintISSN><SeriesTitle Language="En">Lecture Notes in Mathematics</SeriesTitle></SeriesInfo><SeriesHeader><EditorGroup><Editor AffiliationIDS="Aff1"><EditorName DisplayOrder="Western"><GivenName>J.</GivenName><GivenName>-M.</GivenName><FamilyName>Morel</FamilyName></EditorName></Editor><Editor AffiliationIDS="Aff2"><EditorName DisplayOrder="Western"><GivenName>F.</GivenName><FamilyName>Takens</FamilyName></EditorName></Editor><Editor AffiliationIDS="Aff3"><EditorName DisplayOrder="Western"><GivenName>B.</GivenName><FamilyName>Teissier</FamilyName></EditorName></Editor><Affiliation ID="Aff1"><OrgAddress><Country>Cachan</Country></OrgAddress></Affiliation><Affiliation ID="Aff2"><OrgAddress><Country>Groningen</Country></OrgAddress></Affiliation><Affiliation ID="Aff3"><OrgAddress><Country>Paris</Country></OrgAddress></Affiliation></EditorGroup></SeriesHeader><Book Language="En"><BookInfo BookProductType="Monograph" ContainsESM="No" Language="En" MediaType="eBook" NumberingStyle="ChapterContent" TocLevels="2"><BookID>978-3-540-68481-7</BookID><BookTitle>A Theory of Shape Identification</BookTitle><BookVolumeNumber>1948</BookVolumeNumber><BookSequenceNumber>1948</BookSequenceNumber><BookDOI>10.1007/978-3-540-68481-7</BookDOI><BookTitleID>161642</BookTitleID><BookPrintISBN>978-3-540-68480-0</BookPrintISBN><BookElectronicISBN>978-3-540-68481-7</BookElectronicISBN><BookChapterCount>11</BookChapterCount><BookCopyright><CopyrightHolderName>Springer Berlin Heidelberg</CopyrightHolderName><CopyrightYear>2008</CopyrightYear></BookCopyright><BookSubjectGroup><BookSubject Code="SCM" Type="Primary">Mathematics</BookSubject><BookSubject Code="SCM21006" Priority="1" Type="Secondary">Geometry</BookSubject><BookSubject Code="SCM14034" Priority="2" Type="Secondary">Visualization</BookSubject><BookSubject Code="SCI22021" Priority="3" Type="Secondary">Image Processing and Computer Vision</BookSubject><BookSubject Code="SCI21017" Priority="4" Type="Secondary">Artificial Intelligence (incl. Robotics)</BookSubject><BookSubject Code="SCI22005" Priority="5" Type="Secondary">Computer Imaging, Vision, Pattern Recognition and Graphics</BookSubject><BookSubject Code="SCM13011" Priority="6" Type="Secondary">Game Theory, Economics, Social and Behav. Sciences</BookSubject><SubjectCollection Code="SUCO11649">Mathematics and Statistics</SubjectCollection></BookSubjectGroup></BookInfo><BookHeader><AuthorGroup><Author AffiliationIDS="Aff4"><AuthorName DisplayOrder="Western"><GivenName>Frédéric</GivenName><FamilyName>Cao</FamilyName></AuthorName><Contact><Email>fcao@dxo.com</Email></Contact></Author><Author AffiliationIDS="Aff5"><AuthorName DisplayOrder="Western"><GivenName>José-Luis</GivenName><FamilyName>Lisani</FamilyName></AuthorName><Contact><Email>joseluis.lisani@uib.es</Email></Contact></Author><Author AffiliationIDS="Aff6"><AuthorName DisplayOrder="Western"><GivenName>Jean-Michel</GivenName><FamilyName>Morel</FamilyName></AuthorName><Contact><Email>morel@cmla.ens-cachan.fr</Email></Contact></Author><Author AffiliationIDS="Aff7"><AuthorName DisplayOrder="Western"><GivenName>Pablo</GivenName><FamilyName>Musé</FamilyName></AuthorName><Contact><Email>pmuse@fing.edu.uy</Email></Contact></Author><Author AffiliationIDS="Aff8"><AuthorName DisplayOrder="Western"><GivenName>Frédéric</GivenName><FamilyName>Sur</FamilyName></AuthorName><Contact><Email>sur@loria.fr</Email></Contact></Author><Affiliation ID="Aff4"><OrgName>DxO Labs</OrgName><OrgAddress><Street>3 rue Nationale</Street><Postcode>92100 Boulogne Billancourt</Postcode><Country>France</Country></OrgAddress></Affiliation><Affiliation ID="Aff5"><OrgDivision>Dep. Matemàtiques i Informàtica</OrgDivision><OrgName>University Balearic Islands</OrgName><OrgAddress><Street>ctra. Valldemossa km.7,5</Street><City>Balears</City><Postcode>07122 Palma de Mallorca</Postcode><Country>Spain</Country></OrgAddress></Affiliation><Affiliation ID="Aff6"><OrgDivision>Ecole Normale Supérieure de Cachan</OrgDivision><OrgName>CMLA</OrgName><OrgAddress><Street>61 av. du Président Wilson</Street><Postcode>94235 Cachan Cédex</Postcode><Country>France</Country></OrgAddress></Affiliation><Affiliation ID="Aff7"><OrgName>Instituto de Ingeniería Eléctrica</OrgName><OrgAddress><Street>Julio Herrera y Reissig 565</Street><Postcode>11300 Montevideo</Postcode><Country>Uruguay</Country></OrgAddress></Affiliation><Affiliation ID="Aff8"><OrgName>Loria Bat. C - projet Magrit Campus Scientifique</OrgName><OrgAddress><Street>54506 Vandoeuvre-lès-Nancy Cédex</Street><Postcode>BP 239</Postcode><Country>France</Country></OrgAddress></Affiliation></AuthorGroup></BookHeader><Part ID="Part1"><PartInfo TocLevels="0"><PartID>1</PartID><PartNumber>I</PartNumber><PartSequenceNumber>1</PartSequenceNumber><PartTitle>Extracting Image boundaries</PartTitle><PartChapterCount>2</PartChapterCount></PartInfo><Chapter ID="Chap2" Language="En"><ChapterInfo ChapterType="OriginalPaper" ContainsESM="No" NumberingStyle="ChapterContent" TocLevels="0"><ChapterID>2</ChapterID><ChapterNumber>2</ChapterNumber><ChapterDOI>10.1007/978-3-540-68481-7_2</ChapterDOI><ChapterSequenceNumber>2</ChapterSequenceNumber><ChapterTitle Language="En">Extracting Meaningful Curves from Images</ChapterTitle><ChapterFirstPage>15</ChapterFirstPage><ChapterLastPage>35</ChapterLastPage><ChapterCopyright><CopyrightHolderName>Springer-Verlag Berlin Heidelberg</CopyrightHolderName><CopyrightYear>2008</CopyrightYear></ChapterCopyright><ChapterGrants Type="Regular"><MetadataGrant Grant="OpenAccess"></MetadataGrant><AbstractGrant Grant="OpenAccess"></AbstractGrant><BodyPDFGrant Grant="Restricted"></BodyPDFGrant><BodyHTMLGrant Grant="Restricted"></BodyHTMLGrant><BibliographyGrant Grant="Restricted"></BibliographyGrant><ESMGrant Grant="Restricted"></ESMGrant></ChapterGrants><ChapterContext><SeriesID>304</SeriesID><PartID>1</PartID><BookID>978-3-540-68481-7</BookID><BookTitle>A Theory of Shape Identification</BookTitle></ChapterContext></ChapterInfo><ChapterHeader><Abstract ID="Abs1" Language="En"><Para TextBreak="No">The set of level lines of an image (isophotes) or topographic map is a complete and contrast invariant representation of an image. Level lines are ordered by inclusion in a tree structure. These two structure properties make level lines excellent candidates to shape representatives. However, some complexity issues have to be handled: The number of level lines in eight-bits encoded images of size 512×512 is typically 10<Superscript>5</Superscript>. Most of them are very small lines due to noise or micro-texture. So the stable level lines must be selected, namely the ones that are likely to correspond to image contours. The starting point is the MSER method, a variant of the Monasse and Guichard Fast Level Set Transform. The MSER selects a set of level lines which are local extrema of contrast. This method will be put in the Helmholtz framework, following the <Emphasis Type="Italic">a contrario</Emphasis> boundary detection algorithm by Desolneux, Moisan and Morel [51], [54] and two powerful recent variants. The experiments in this chapter will show that selecting the most meaningful level lines reduces their number by a factor 100 without significant shape contents loss.</Para><Para TextBreak="No">A method which selects one out of hundred level lines in the image without significant information loss is necessarily sophisticated. Sect. 2.1 briefly reviews the level line tree of a digital image. Sect. 2.2 describes a first way to extract well contrasted level lines, the MSER method. Sect. 2.3 makes an account of the Desolneux et al. maximal meaningful boundaries and Sect. 2.4 gives a mathematical justification which was actually missing in the original theory. Sect. 2.5 is devoted to a multiscale extension which avoids missing boundaries because of high noise level and Sect. 2.6 deals with the so called “blue sky” effect which can lead to over-detections in textured parts of the image.</Para></Abstract></ChapterHeader><NoBody></NoBody></Chapter></Part></Book></Series></Publisher></istex:document></istex:metadataXml><mods version="3.6"><titleInfo lang="en"><title>Extracting Meaningful Curves from Images</title></titleInfo><titleInfo type="alternative" contentType="CDATA"><title>Extracting Meaningful Curves from Images</title></titleInfo><name type="personal"><namePart type="given">Frédéric</namePart><namePart type="family">Cao</namePart><affiliation>DxO Labs, 3 rue Nationale, 92100 Boulogne Billancourt, France</affiliation><affiliation>E-mail: fcao@dxo.com</affiliation></name><name type="personal"><namePart type="given">José-Luis</namePart><namePart type="family">Lisani</namePart><affiliation>Dep. Matemàtiques i Informàtica, University Balearic Islands, ctra. Valldemossa km.7,5, 07122 Palma de Mallorca, Balears, Spain</affiliation><affiliation>E-mail: joseluis.lisani@uib.es</affiliation></name><name type="personal"><namePart type="given">Jean-Michel</namePart><namePart type="family">Morel</namePart><affiliation>Ecole Normale Supérieure de Cachan, CMLA, 61 av. du Président Wilson, 94235 Cachan Cédex, France</affiliation><affiliation>E-mail: morel@cmla.ens-cachan.fr</affiliation></name><name type="personal"><namePart type="given">Pablo</namePart><namePart type="family">Musé</namePart><affiliation>Instituto de Ingeniería Eléctrica, Julio Herrera y Reissig 565, 11300 Montevideo, Uruguay</affiliation><affiliation>E-mail: pmuse@fing.edu.uy</affiliation></name><name type="personal"><namePart type="given">Frédéric</namePart><namePart type="family">Sur</namePart><affiliation>Loria Bat. C - projet Magrit Campus Scientifique, 54506 Vandoeuvre-lès-Nancy Cédex, BP 239, France</affiliation><affiliation>E-mail: sur@loria.fr</affiliation></name><typeOfResource>text</typeOfResource><genre displayLabel="OriginalPaper" authority="ISTEX" authorityURI="https://content-type.data.istex.fr" type="research-article" valueURI="https://content-type.data.istex.fr/ark:/67375/XTP-1JC4F85T-7">research-article</genre><originInfo><publisher>Springer Berlin Heidelberg</publisher><place><placeTerm type="text">Berlin, Heidelberg</placeTerm></place><dateIssued encoding="w3cdtf">2008</dateIssued><copyrightDate encoding="w3cdtf">2008</copyrightDate></originInfo><language><languageTerm type="code" authority="rfc3066">en</languageTerm><languageTerm type="code" authority="iso639-2b">eng</languageTerm></language><abstract lang="en">The set of level lines of an image (isophotes) or topographic map is a complete and contrast invariant representation of an image. Level lines are ordered by inclusion in a tree structure. These two structure properties make level lines excellent candidates to shape representatives. However, some complexity issues have to be handled: The number of level lines in eight-bits encoded images of size 512×512 is typically 105. Most of them are very small lines due to noise or micro-texture. So the stable level lines must be selected, namely the ones that are likely to correspond to image contours. The starting point is the MSER method, a variant of the Monasse and Guichard Fast Level Set Transform. The MSER selects a set of level lines which are local extrema of contrast. This method will be put in the Helmholtz framework, following the a contrario boundary detection algorithm by Desolneux, Moisan and Morel [51], [54] and two powerful recent variants. The experiments in this chapter will show that selecting the most meaningful level lines reduces their number by a factor 100 without significant shape contents loss. A method which selects one out of hundred level lines in the image without significant information loss is necessarily sophisticated. Sect. 2.1 briefly reviews the level line tree of a digital image. Sect. 2.2 describes a first way to extract well contrasted level lines, the MSER method. Sect. 2.3 makes an account of the Desolneux et al. maximal meaningful boundaries and Sect. 2.4 gives a mathematical justification which was actually missing in the original theory. Sect. 2.5 is devoted to a multiscale extension which avoids missing boundaries because of high noise level and Sect. 2.6 deals with the so called “blue sky” effect which can lead to over-detections in textured parts of the image.</abstract><relatedItem type="host"><titleInfo><title>A Theory of Shape Identification</title></titleInfo><name type="personal"><namePart type="given">Frédéric</namePart><namePart type="family">Cao</namePart><affiliation>DxO Labs, 3 rue Nationale, 92100 Boulogne Billancourt, France</affiliation><affiliation>E-mail: fcao@dxo.com</affiliation></name><name type="personal"><namePart type="given">José-Luis</namePart><namePart type="family">Lisani</namePart><affiliation>Dep. Matemàtiques i Informàtica, University Balearic Islands, ctra. Valldemossa km.7,5, 07122 Palma de Mallorca, Balears, Spain</affiliation><affiliation>E-mail: joseluis.lisani@uib.es</affiliation></name><name type="personal"><namePart type="given">Jean-Michel</namePart><namePart type="family">Morel</namePart><affiliation>Ecole Normale Supérieure de Cachan, CMLA, 61 av. du Président Wilson, 94235 Cachan Cédex, France</affiliation><affiliation>E-mail: morel@cmla.ens-cachan.fr</affiliation></name><name type="personal"><namePart type="given">Pablo</namePart><namePart type="family">Musé</namePart><affiliation>Instituto de Ingeniería Eléctrica, Julio Herrera y Reissig 565, 11300 Montevideo, Uruguay</affiliation><affiliation>E-mail: pmuse@fing.edu.uy</affiliation></name><name type="personal"><namePart type="given">Frédéric</namePart><namePart type="family">Sur</namePart><affiliation>Loria Bat. C - projet Magrit Campus Scientifique, 54506 Vandoeuvre-lès-Nancy Cédex, BP 239, France</affiliation><affiliation>E-mail: sur@loria.fr</affiliation></name><genre type="book-series" authority="ISTEX" authorityURI="https://publication-type.data.istex.fr" valueURI="https://publication-type.data.istex.fr/ark:/67375/JMC-0G6R5W5T-Z">book-series</genre><originInfo><publisher>Springer</publisher><copyrightDate encoding="w3cdtf">2008</copyrightDate><issuance>monographic</issuance></originInfo><subject><genre>Book-Subject-Collection</genre><topic authority="SpringerSubjectCodes" authorityURI="SUCO11649">Mathematics and Statistics</topic></subject><subject><genre>Book-Subject-Group</genre><topic authority="SpringerSubjectCodes" authorityURI="SCM">Mathematics</topic><topic authority="SpringerSubjectCodes" authorityURI="SCM21006">Geometry</topic><topic authority="SpringerSubjectCodes" authorityURI="SCM14034">Visualization</topic><topic authority="SpringerSubjectCodes" authorityURI="SCI22021">Image Processing and Computer Vision</topic><topic authority="SpringerSubjectCodes" authorityURI="SCI21017">Artificial Intelligence (incl. Robotics)</topic><topic authority="SpringerSubjectCodes" authorityURI="SCI22005">Computer Imaging, Vision, Pattern Recognition and Graphics</topic><topic authority="SpringerSubjectCodes" authorityURI="SCM13011">Game Theory, Economics, Social and Behav. Sciences</topic></subject><identifier type="DOI">10.1007/978-3-540-68481-7</identifier><identifier type="ISBN">978-3-540-68480-0</identifier><identifier type="eISBN">978-3-540-68481-7</identifier><identifier type="ISSN">0075-8434</identifier><identifier type="BookTitleID">161642</identifier><identifier type="BookID">978-3-540-68481-7</identifier><identifier type="BookChapterCount">11</identifier><identifier type="BookVolumeNumber">1948</identifier><identifier type="BookSequenceNumber">1948</identifier><identifier type="PartChapterCount">2</identifier><part><date>2008</date><detail type="part"><title>I: Extracting Image boundaries</title></detail><detail type="volume"><number>1948</number><caption>vol.</caption></detail><detail type="chapter"><number>2</number><caption>chapter</caption></detail><extent unit="pages"><start>15</start><end>35</end></extent></part><recordInfo><recordOrigin>Springer Berlin Heidelberg, 2008</recordOrigin></recordInfo></relatedItem><relatedItem type="series"><titleInfo><title>Lecture Notes in Mathematics</title></titleInfo><name type="personal"><namePart type="given">J.</namePart><namePart type="given">-M.</namePart><namePart type="family">Morel</namePart><affiliation>Cachan</affiliation><role><roleTerm type="text">editor</roleTerm></role></name><name type="personal"><namePart type="given">F.</namePart><namePart type="family">Takens</namePart><affiliation>Groningen</affiliation><role><roleTerm type="text">editor</roleTerm></role></name><name type="personal"><namePart type="given">B.</namePart><namePart type="family">Teissier</namePart><affiliation>Paris</affiliation><role><roleTerm type="text">editor</roleTerm></role></name><originInfo><publisher>Springer</publisher><copyrightDate encoding="w3cdtf">2008</copyrightDate><issuance>serial</issuance></originInfo><identifier type="ISSN">0075-8434</identifier><identifier type="SeriesID">304</identifier><part><detail type="volume"><number>I</number><caption>vol.</caption></detail><detail type="chapter"><number>2</number></detail></part><recordInfo><recordOrigin>Springer Berlin Heidelberg, 2008</recordOrigin></recordInfo></relatedItem><identifier type="istex">247E8CE7C3BBEAB502372C25E886D4F903F4A476</identifier><identifier type="ark">ark:/67375/HCB-M2WBVBBM-9</identifier><identifier type="DOI">10.1007/978-3-540-68481-7_2</identifier><identifier type="ChapterID">2</identifier><identifier type="ChapterID">Chap2</identifier><accessCondition type="use and reproduction" contentType="copyright">Springer Berlin Heidelberg, 2008</accessCondition><recordInfo><recordContentSource authority="ISTEX" authorityURI="https://loaded-corpus.data.istex.fr" valueURI="https://loaded-corpus.data.istex.fr/ark:/67375/XBH-RLRX46XW-4">springer</recordContentSource><recordOrigin>Springer-Verlag Berlin Heidelberg, 2008</recordOrigin></recordInfo></mods><json:item><extension>json</extension><original>false</original><mimetype>application/json</mimetype><uri>https://api.istex.fr/ark:/67375/HCB-M2WBVBBM-9/record.json</uri></json:item></metadata><annexes><json:item><extension>xml</extension><original>true</original><mimetype>application/xml</mimetype><uri>https://api.istex.fr/ark:/67375/HCB-M2WBVBBM-9/annexes.xml</uri></json:item></annexes></istex></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/Istex/Corpus
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000824 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Istex/Corpus/biblio.hfd -nk 000824 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/Lorraine
|area= InforLorV4
|flux= Istex
|étape= Corpus
|type= RBID
|clé= ISTEX:247E8CE7C3BBEAB502372C25E886D4F903F4A476
|texte= Extracting Meaningful Curves from Images
}}
| This area was generated with Dilib version V0.6.33. |  |