We propose using the inner-distance between landmark points to build shape descriptors. The inner-distance is defined as the length of the shortest path between landmark points within the shape silhouette. We show that the inner-distance is articulation insensitive and more effective at capturing complex shapes with part structures than Euclidean distance. To demonstrate this idea, it is used to build a new shape descriptor based on shape contexts. After that, we design a dynamic programming based method for shape matching and comparison. We have tested our approach on a variety of shape databases including an articulated shape dataset, MPEG7 CE-Shape-1, Kimia silhouettes, a Swedish leaf database and a human motion silhouette dataset. In all the experiments, our method demonstrates effective performance compared with other algorithms.
Using the inner-distance for classification of articulated shapes
2005-01-01
470793 byte
Conference paper
Electronic Resource
English
Representation and Matching of Articulated Shapes
British Library Conference Proceedings | 2004
|Representation and matching of articulated shapes
IEEE | 2004
|Matching 2D and 3D articulated shapes using the eccentricity transform
British Library Online Contents | 2011
|Optimal shapes and winding parameters for filament wound articulated vessels
Tema Archive | 2008
|LEARNING THE DISTANCE BETWEEN CAMERAS FOR ARTICULATED VEHICLES
European Patent Office | 2020
|