Strong image segmentation is a very challenging problem in computer vision research. Both data-driven and model-driven approaches have been investigated in the past two decades, and many approaches proposed. Although model-based approaches are more promising in addressing strong image segmentation, data-driven approaches present more general frameworks which could potentially be adopted to segment general scenes without any prior model information. We discuss the problems of strong image segmentation from a data-driven perspective, and present a modeling technique describing an object with both its segments and a hierarchical relationship among the segments. The paper is devoted to the discussion of the feasibility of data-driven approaches for strong image segmentation. Existing approaches are not suitable for strong image segmentation in complex environments, but preliminary experimental results show the feasibility of our proposed model.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Strong image segmentation from a data-driven perspective: impossible?


    Beteiligte:
    Qiang Zhou, (Autor:in) / Limin Ma, (Autor:in) / Min Zhou, (Autor:in) / Chelberg, D. (Autor:in)


    Erscheinungsdatum :

    2004-01-01


    Format / Umfang :

    450527 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Impossible architectures?

    Polit-Casillas, Raul | NTRS | 2017


    Impossible spectroscopy?

    Emerald Group Publishing | 2005


    Image segmentation by data driven Markov chain Monte Carlo

    Zhuowen Tu, / Song-Chun Zhu, / Heung-Yeung Shum, | IEEE | 2001


    Engineering the impossible

    Online Contents | 2009


    The impossible equation

    Condom, Pierre | Online Contents | 1996