Title :
Parsing Silhouettes without Boundary Curvature
Author :
Juengling, Ralf ; Prasad, Lakshman
Author_Institution :
Portland State Univ., Portland
Abstract :
We describe a new decomposition algorithm for two-dimensional, polygonal shapes. The algorithm first finds a set of overlapping ribbon-like subshapes ("ribbons") by grouping skeleton fragments into long smooth spines. The parts are then obtained by cutting the ribbons along lines of mutual intersection. With this approach we find part cuts that obey heuristic rules of early vision (M. Singh et a., 1999) without using boundary curvature.
Keywords :
mesh generation; object recognition; optimisation; Delaunay triangulation; decomposition algorithm; heuristic rules; long smooth spines; object recognition; overlapping ribbon-like subshapes; polygonal shapes; silhouettes parsing; skeleton fragment grouping; Computer science; Detectors; Image edge detection; Joining processes; Length measurement; Object recognition; Pixel; Q measurement; Shape; Skeleton; Delaunay triangulation; Perceptual Grouping; Saliency Network; Shape Decomposition;
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.2007.4362853