SHAPE AND TEXTURE INDEXES APPLICATION TO CELL NUCLEI CLASSIFICATION

DOI Web Site 被引用文献3件
  • GUILLAUME THIBAULT
    Center for Mathematical Morphology (CMM), Mathématiques et Systèmes, Mines-ParisTech, 35 rue St Honoré, Fontainebleau, 77300, France
  • BERNARD FERTIL
    LSIS (Laboratoire des Sciences de l'Information et des Systèmes), UMR CNRS 6168, Aix-Marseille University, 168 Avenue de Luminy, 13288 Marseille Cedex 9, France
  • CLAIRE NAVARRO
    INSERM UMR 910, Medical Genetic and Functional Genomic, Medical School, Marseille, France
  • SANDRINE PEREIRA
    INSERM UMR 910, Medical Genetic and Functional Genomic, Medical School, Marseille, France
  • PIERRE CAU
    INSERM UMR 910, Medical Genetic and Functional Genomic, Medical School, Marseille, France
  • NICOLAS LEVY
    INSERM UMR 910, Medical Genetic and Functional Genomic, Medical School, Marseille, France
  • JEAN SEQUEIRA
    LSIS (Laboratoire des Sciences de l'Information et des Systèmes), UMR CNRS 6168, Aix-Marseille University, 168 Avenue de Luminy, 13288 Marseille Cedex 9, France
  • JEAN-LUC MARI
    LSIS (Laboratoire des Sciences de l'Information et des Systèmes), UMR CNRS 6168, Aix-Marseille University, 168 Avenue de Luminy, 13288 Marseille Cedex 9, France

説明

<jats:p>This paper describes the sequence of construction of a cell nuclei classification model by the analysis, the characterization and the classification of shape and texture. We describe first the elaboration of dedicated shape indexes and second the construction of the associated classification submodel. Then we present a new method of texture characterization, based on the construction and the analysis of statistical matrices encoding the texture. The various characterization techniques developed in this paper are systematically compared to previous approaches. In particular, we paid special attention to the results obtained by a versatile classification method using a large range of descriptors dedicated to the characterization of shapes and textures. Finally, the last classifier built with our methods achieved 88% of classification out of the 94% possible.</jats:p>

収録刊行物

被引用文献 (3)*注記

もっと見る

詳細情報 詳細情報について

問題の指摘

ページトップへ