X-Git-Url: https://bilbo.iut-bm.univ-fcomte.fr/and/gitweb/these_gilles.git/blobdiff_plain/82c062292d36ed7f5cb8e3e913382ca8c47eb379..2145c00e2163c4976cfc5dd2937ac2b5e7515892:/THESE/these.toc?ds=sidebyside diff --git a/THESE/these.toc b/THESE/these.toc index df5542d..7e51dda 100644 --- a/THESE/these.toc +++ b/THESE/these.toc @@ -9,22 +9,28 @@ \contentsline {subsection}{\numberline {2.2.4}Le bruit de Poisson}{13}{subsection.2.2.4} \contentsline {section}{\numberline {2.3}Les techniques de r\IeC {\'e}duction de bruit}{13}{section.2.3} \contentsline {subsection}{\numberline {2.3.1}Les op\IeC {\'e}rateurs de base}{14}{subsection.2.3.1} -\contentsline {subsubsection}{\numberline {2.3.1.1}Les algorithmes de voisinage}{14}{subsubsection.2.3.1.1} -\contentsline {subsubsection}{\numberline {2.3.1.2}Les algorithmes par dictionnaire}{16}{subsubsection.2.3.1.2} -\contentsline {subsection}{\numberline {2.3.2}Les techniques avanc\IeC {\'e}es}{18}{subsection.2.3.2} +\contentsline {subsubsection}{\numberline {2.3.1.1}Le filtre de convolution}{14}{subsubsection.2.3.1.1} +\contentsline {subsubsection}{\numberline {2.3.1.2}Le filtre m\IeC {\'e}dian}{15}{subsubsection.2.3.1.2} +\contentsline {subsubsection}{\numberline {2.3.1.3}Le filtre bilat\IeC {\'e}ral}{16}{subsubsection.2.3.1.3} +\contentsline {subsubsection}{\numberline {2.3.1.4}Les algorithmes de filtrage par dictionnaire}{18}{subsubsection.2.3.1.4} +\contentsline {subsection}{\numberline {2.3.2}Les algorithmes de filtrage par patches}{18}{subsection.2.3.2} \contentsline {section}{\numberline {2.4}Les impl\IeC {\'e}mentations GPU des algorithmes de filtrage}{19}{section.2.4} -\contentsline {section}{\numberline {2.5}Les techniques de segmentation}{21}{section.2.5} -\contentsline {subsection}{\numberline {2.5.1}Analyse d'histogramme}{22}{subsection.2.5.1} -\contentsline {subsection}{\numberline {2.5.2}Analyse de graphe}{23}{subsection.2.5.2} -\contentsline {subsection}{\numberline {2.5.3}kernel-means, mean-shift et d\IeC {\'e}riv\IeC {\'e}s}{25}{subsection.2.5.3} -\contentsline {subsection}{\numberline {2.5.4}Les contours actifs, ou \textit {snakes}}{27}{subsection.2.5.4} -\contentsline {subsection}{\numberline {2.5.5}M\IeC {\'e}thodes hybrides}{29}{subsection.2.5.5} -\contentsline {section}{\numberline {2.6}L'\IeC {\'e}tat de l'art des impl\IeC {\'e}mentations GPU}{29}{section.2.6} -\contentsline {chapter}{\numberline {3}La segmentation orient\IeC {\'e}e r\IeC {\'e}gions dans les images bruit\IeC {\'e}es}{31}{chapter.3} -\contentsline {section}{\numberline {3.1}Pr\IeC {\'e}sentation - existant}{31}{section.3.1} -\contentsline {section}{\numberline {3.2}La parall\IeC {\`e}lisation du snake polygonal}{31}{section.3.2} -\contentsline {chapter}{\numberline {4}Le filtrage des images sur GPU}{33}{chapter.4} -\contentsline {section}{\numberline {4.1}Algorithme de r\IeC {\'e}duction de bruit par recherche des lignes de niveaux}{33}{section.4.1} -\contentsline {section}{\numberline {4.2}Filtre m\IeC {\'e}dian}{33}{section.4.2} -\contentsline {section}{\numberline {4.3}Filtres de convolution}{33}{section.4.3} -\contentsline {chapter}{\numberline {5}Conclusion g\IeC {\'e}n\IeC {\'e}rale}{35}{chapter.5} +\contentsline {subsection}{\numberline {2.4.1}Le filtrage par convolution}{20}{subsection.2.4.1} +\contentsline {subsection}{\numberline {2.4.2}Le filtre m\IeC {\'e}dian}{20}{subsection.2.4.2} +\contentsline {subsection}{\numberline {2.4.3}Le filtre bilat\IeC {\'e}ral}{21}{subsection.2.4.3} +\contentsline {subsection}{\numberline {2.4.4}Les filtres par patches}{22}{subsection.2.4.4} +\contentsline {section}{\numberline {2.5}Les techniques de segmentation}{23}{section.2.5} +\contentsline {subsection}{\numberline {2.5.1}Analyse d'histogramme}{23}{subsection.2.5.1} +\contentsline {subsection}{\numberline {2.5.2}Analyse de graphe}{24}{subsection.2.5.2} +\contentsline {subsection}{\numberline {2.5.3}kernel-means, mean-shift et d\IeC {\'e}riv\IeC {\'e}s}{26}{subsection.2.5.3} +\contentsline {subsection}{\numberline {2.5.4}Les contours actifs, ou \textit {snakes}}{28}{subsection.2.5.4} +\contentsline {subsection}{\numberline {2.5.5}M\IeC {\'e}thodes hybrides}{30}{subsection.2.5.5} +\contentsline {section}{\numberline {2.6}L'\IeC {\'e}tat de l'art des impl\IeC {\'e}mentations GPU}{31}{section.2.6} +\contentsline {chapter}{\numberline {3}La segmentation orient\IeC {\'e}e r\IeC {\'e}gions dans les images bruit\IeC {\'e}es}{33}{chapter.3} +\contentsline {section}{\numberline {3.1}Pr\IeC {\'e}sentation - existant}{33}{section.3.1} +\contentsline {section}{\numberline {3.2}La parall\IeC {\`e}lisation du snake polygonal}{33}{section.3.2} +\contentsline {chapter}{\numberline {4}Le filtrage des images sur GPU}{35}{chapter.4} +\contentsline {section}{\numberline {4.1}Algorithme de r\IeC {\'e}duction de bruit par recherche des lignes de niveaux}{35}{section.4.1} +\contentsline {section}{\numberline {4.2}Filtre m\IeC {\'e}dian}{35}{section.4.2} +\contentsline {section}{\numberline {4.3}Filtres de convolution}{35}{section.4.3} +\contentsline {chapter}{\numberline {5}Conclusion g\IeC {\'e}n\IeC {\'e}rale}{37}{chapter.5}