The automated segmentation of images into semantically meaningful parts requires shape information since lowlevel feature analysis alone often fails to reach this goal. We introduce a novel method of shape constrained image segmentation which is based on mixtures of feature distributions for color and texture as well as probabilistic shape knowledge. The combined approach is formulated in the framework of Bayesian statistics to account for the robustness requirement in image understanding. Experimental evidence shows that semantically meaningful segments are inferred, even when image data alone gives rise to ambiguous segmentations.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Shape constrained image segmentation by parametric distributional clustering


    Beteiligte:
    Zoller, T. (Autor:in) / Buhmann, J.M. (Autor:in)


    Erscheinungsdatum :

    01.01.2004


    Format / Umfang :

    911810 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Shape Constrained Image Segmentation by Parametric Distributional Clustering

    Zoller, T. / Buhmann, J. / IEEE Computer Society | British Library Conference Proceedings | 2004


    On combining graph-partitioning with non-parametric clustering for image segmentation

    Martinez, A. M. / Mittrapiyanuruk, P. / Kak, A. C. | British Library Online Contents | 2004


    Global structure constrained local shape prior estimation for medical image segmentation

    Yan, P. / Zhang, W. / Turkbey, B. et al. | British Library Online Contents | 2013



    Partial sparse shape constrained sector-driven bladder wall segmentation

    Qin, X. / Lu, H. / Tian, Y. et al. | British Library Online Contents | 2015