As mentioned in many papers, a lot of key parameters of image segmentation algorithms are manually tuned by de- signers. This induces a lack of flexibility of the segmentation step in many vision systems. By a dynamic control of these parameters, results of this crucial step could be drastically improved. We propose a scheme to automatically select segmentation algorithm and tune theirs key parameters thanks to a preliminary supervised learning stage. This paper details this learning approach which is composed by three steps: (1) optimal parameters extraction, (2) algorithm selection learning, and (3) generalization of parametrization learning. The major contribution is twofold: segmentation is adapted to the image to segment, and in the same time, this scheme can be used as a generic framework, independant of any application domain.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    A Learning Approach for Adaptive Image Segmentation


    Beteiligte:
    Martin, V. (Autor:in) / Thonnat, M. (Autor:in) / Maillot, N. (Autor:in)


    Erscheinungsdatum :

    01.01.2006


    Format / Umfang :

    697606 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Image Segmentation by Learning Approach

    Legal-Ayala, H. / Facon, J. / Institute of Electrical and Electronics Engineers | British Library Conference Proceedings | 2003


    Image segmentation by learning approach

    Legal-Ayala, H.A. / Facon, J. | IEEE | 2003


    Adaptive Bayesian approach for color image segmentation [2094-81]

    Chang, M. M. / Patti, A. J. / Sezan, M. I. et al. | British Library Conference Proceedings | 1993


    Segmentation approach by learning: different image applications

    Legal-Ayala, H.A. / Facon, J. | IEEE | 2003


    Segmentation Approach by Learning: Different Image Aplications

    Ayala, H. / Facon, J. / IEEE | British Library Conference Proceedings | 2003