In this paper, we present a novel solution of image segmentation based on positiveness by regarding the segmentation as one of the graph-theoretic clustering problems. On the contrary to spectral clustering methods using eigenvectors, the proposed method tries to find an additive combination of positive components from an originally positive data-driven matrix. By using the positiveness constraint, we obtain sparsely clustered results which are closely related to human perception and thus we call this method sparse clustering. The proposed method adopts a binary tree structure and solves a model selection problem by automatically determining the number of clusters using intra- and inter-cluster measures. We tested our method with various kinds of data such as points, gray-scale, color, and texture images. Experimental results show that the proposed method provides very successful and encouraging segmentations.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Image Segmentation by Unsupervised Sparse Clustering


    Beteiligte:
    Jeon, Byoung-Ki (Autor:in) / Jung, Yun-Beom (Autor:in) / Hong, Ki-Sang (Autor:in)


    Erscheinungsdatum :

    2005-01-01


    Format / Umfang :

    630398 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Unsupervised scene segmentation using sparse coding context

    Liu, Y. C. / Chen, H. T. | British Library Online Contents | 2013



    Unsupervised texture image segmentation using multilayer data condensation spectral clustering

    Liu, H. / Jiao, L. / Zhao, F. | British Library Online Contents | 2010


    Unsupervised Fuzzy Clustering and Image Segmentation Using Weighted Neural Networks

    Muhammed, H. / IEEE | British Library Conference Proceedings | 2003


    Unsupervised Multiscale Image Segmentation

    Kam, A. / Fitzgerald, W. / IEEE | British Library Conference Proceedings | 1999