Edges at multiple scales provide complementary grouping cues for image segmentation. These cues are reliable within different ranges. The larger the scale of an edge, the longer range the grouping cues it designates, and the greater impact it has on the final segmentation. A good segmentation respects grouping cues at each scale. These intuitions are formulated in a graph-theoretic framework where multiscale edges define pairwise pixel affinity at multiple grids, each captured in one graph. A novel criterion called average cuts of normalized affinity is proposed to evaluate a simultaneous segmentation through all these graphs. Its near-global optima can be solved efficiently. With a sparse yet complete characterization of pairwise pixel affinity, this graph-cuts approach leads to a hierarchy of coarse to fine segmentations that naturally take care of textured regions and weak contours.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Segmentation using multiscale cues


    Contributors:
    Yu, S.X. (author)


    Publication date :

    2004-01-01


    Size :

    1420220 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Segmentation Using Multiscale Cues

    Yu, S. / IEEE Computer Society | British Library Conference Proceedings | 2004


    Multiscale segmentation by combining motion and intensity cues

    Meirav Galun, / Alexander Apartsin, / Ronen Basri, | IEEE | 2005


    Range segmentation using focus cues

    Changhoon Yim / Bovik, A.C. | IEEE | 1995


    Range Segmentation Using Focus Cues

    Yim, C. / Bovic, A. C. / IEEE; Computer Society; Technical Committee for Pattern Analysis and Machine Intelligence | British Library Conference Proceedings | 1995


    Adaptive Multiple Object Tracking Using Colour and Segmentation Cues

    Kumar, Pankaj / Brooks, Michael J. / Dick, Anthony | Springer Verlag | 2007