A new method to pre-segment images by means of a hierarchical description is proposed. This description is obtained from an investigation of the deep structure of a scale space image-the input image and the Gaussian filtered ones simultaneously. We concentrate on scale space critical points-points with vanishing gradient with respect to both spatial and scale direction. We show that these points are always saddle points. They turn out to be extremely useful, since the iso-intensity manifolds through these points provide a scale space hierarchy tree and induce a segmentation without a priori knowledge. Moreover, together with the so-called catastrophe points, these scale space saddles form the critical points of the parameterised critical curves-the curves along which the spatial saddle points move in scale space. Experimental results with respect to the hierarchy and segmentation are given, based on an artificial image and a simulated MRI.
Hierarchical pre-segmentation without prior knowledge
Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001 ; 2 ; 487-493 vol.2
2001-01-01
724772 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Hierarchical Pre-Segmentation without Prior Knowledge
British Library Conference Proceedings | 2001
|Symbol recognition without prior segmentation [2181-30]
British Library Conference Proceedings | 1994
|Watershed segmentation using prior shape and appearance knowledge
British Library Online Contents | 2009
|Drift Control for Path Tracking Without Prior Knowledge of Drift Equilibria
Springer Verlag | 2020
|