Title :
Surface Segmentation through Concentrated Curvature
Author :
Mesmoudi, Mohammed Mostefa ; Danovaro, Emanuele ; De Floriani, Leila ; Port, Umberto
Author_Institution :
Univ. of Mostaganem, Mostaganem
Abstract :
Curvature is one of the most relevant notions that links the metric properties of a surface to its geometry and to its topology (Gauss-Bonnet theorem). In the literature, a variety of approaches exist to compute curvatures in the discrete case. Several techniques are computationally intensive or suffer from convergence problems. In this paper, we discuss the notion of concentrated curvature, introduced by Troyanov [24]. We discuss properties of this curvature and compare with a widely-used technique that estimates the Gaussian curvatures on a triangulated surface. We apply our STD method [13] for terrain segmentation to segment a surface by using different curvature approaches and we illustrate our comparisons through examples.
Keywords :
Gaussian processes; image segmentation; Gauss-Bonnet theorem; Gaussian curvatures; concentrated curvature; convergence problems; surface segmentation; terrain segmentation; triangulated surface; Approximation error; Convergence; Educational institutions; Gaussian processes; Geometry; Image analysis; Image segmentation; Shape; Topology;
Conference_Titel :
Image Analysis and Processing, 2007. ICIAP 2007. 14th International Conference on
Conference_Location :
Modena
Print_ISBN :
978-0-7695-2877-9
DOI :
10.1109/ICIAP.2007.4362854