Building on recent progress in modeling filter response statistics of natural images we integrate a statistical model into a variational framework for image segmentation. Incorporated in a sound probabilistic distance measure the model drives level sets toward meaningful segmentations of complex textures and natural scenes. Since each region comprises two model parameters only the approach is computationally efficient and enables the application of variational segmentation to a considerably larger class of real-world images. We validate the statistical basis of our approach on thousands of natural images and demonstrate that our model outperforms recent variational segmentation methods based on second-order statistics.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Natural image statistics for natural image segmentation


    Beteiligte:
    Heiler, (Autor:in) / Schnorr, (Autor:in)


    Erscheinungsdatum :

    01.01.2003


    Format / Umfang :

    414558 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Natural Image Statistics for Natural Image Segmentation

    Heiler, M. / Schnorr, C. / IEEE | British Library Conference Proceedings | 2003


    Natural Image Statistics for Natural Image Segmentation

    Heiler, M. / Schnörr, C. | British Library Online Contents | 2005


    No-reference image quality assessment based on log-derivative statistics of natural scenes

    Zhang, Y. / Chandler, D.M. | British Library Online Contents | 2013


    Image segmentation

    LEVI ISHAY / BAR ZVI ASAF / SCHWARTZ YONATAN et al. | Europäisches Patentamt | 2024

    Freier Zugriff