In differential geometry curves are characterized as mappings from an interval to the plane. In topology curves are characterized as a Hausdorff space with certain countability properties. Neither of these definitions captures the role that curves play in vision, however, in which curves can denote simple objects (such as a straight line), or complicated objects (such as a jumble of string). The difference between these situations is in part a measure of their complexity, and in part a measure of their dimensionality. Note that the map defining such curves is unknown, as is the proper way to represent them. We propose a formal complexity theory of curves appropriate for computational vision in general, and for problems like separating straight lines from jumbles in particular. The theory is applied to the problem of perceptual grouping.<>


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Indexing visual representations through the complexity map


    Contributors:
    Dubuc, B. (author) / Zucker, S.W. (author)


    Publication date :

    1995-01-01


    Size :

    773001 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Indexing Visual Representations through the Complexity Map

    Dubuc, B. / Zucker, S. / IEEE Computer Society et al. | British Library Conference Proceedings | 1995



    Indexing through laplacian spectra

    Demirci, M. F. / van Leuken, R. H. / Veltkamp, R. C. | British Library Online Contents | 2008



    Indexing Images by Trees of Visual Content

    Schweitzer, H. / IEEE; Computer Society | British Library Conference Proceedings | 1998