A skeleton-based approach for detection of perceptually salient features on polygonal surfaces

The paper presents a skeleton-based approach for robust detection of perceptually salient shape features. Given a shape approximated by a polygonal surface, its skeleton is extracted using a three-dimensional Voronoi diagram technique proposed recently by Amenta et al. Shape creases, ridges and ravines, are detected as curves corresponding to skeletal edges. Salient shape regions are extracted via skeleton decomposition into patches. The approach explores the singularity theory for ridge and ravine detection, combines several filtering methods for skeleton denoising and for selecting perceptually important ridges and ravines, and uses a topological analysis of the skeleton for detection of salient shape regions.