A multiscale extension to the medial axis transform(MAT) or skeleton can be obtained by combining information derived from a scale-space hierarchy of boundary representations with region information provided by the MAT. The skeleton-space is constructed by attributing each skeleton component with a hierarchically ordered sequence of residual values, each expressing the saliency of the component at a distinct resolution level. Since our method amounts to a rather symbolic than iconic computation of a multiscale MAT, it does not introduce the correspondence problem between distinct levels of detail, in contrast to other commonly proposed techniques. Our multiscale MAT is capable of describing complex shapes characterized by significantly jagged boundaries. Furthermore, tracking the evolution of prominent loci of the MAT such as nodes across scales permits to assess the most significant skeleton constituents and to automatically determine pruning parameters. A salient subset of the MAT (first order skeleton) can be extracted without the need of manual threshold adjustment.>

A novel method of robust skeletonization based on the Voronoi diagram of boundary points, which is characterized by correct Euclidean metries and inherent preservation of connectivity, is presented. The regularization of the Voronoi medial axis (VMA) in the sense of H. Blum's (1967) prairie fire analogy is done by attributing to each component of the VMA a measure of prominence and stability. The resulting Voronoi skeletons appear largely invariant with respect to typical noise conditions in the image and geometric transformations. Hierarchical clustering of the skeleton branches, the so-called skeleton pyramid, leads to further simplification of the skeleton. Several applications demonstrate the suitability of the Voronoi skeleton to higher-order tasks such as object recognition.>

Discusses the amenability of the medial axis transform (MAT) or skeleton to processes at the intermediate level, which organize low-level primitives to entities on a semantically higher level (perceptual grouping). Several properties of the MAT assist the effective handling of proximity and adjacency relationships. The authors focus on the wealth of information contained in a specific implementation of the MAT on the raster grid, henceforth denoted as Voronoi skeleton.>