We present a novel approach to measuring similarity between shapes and exploit it for object recognition. In our framework, the measurement of similarity is preceded by (1) solving for correspondences between points on the two shapes, (2) using the correspondences to estimate an aligning transform. In order to solve the correspondence problem, we attach a descriptor, the shape context, to each point. The shape context at a reference point captures the distribution of the remaining points relative to it, thus offering a globally discriminative characterization. Corresponding points on two similar shapes will have similar shape contexts, enabling us to solve for correspondences as an optimal assignment problem. Given the point correspondences, we estimate the transformation that best aligns the two shapes; regularized thin-plate splines provide a flexible class of transformation maps for this purpose. Dis-similarity between two shapes is computed as a sum of matching errors between corresponding points, together with a term measuring the magnitude of the aligning transform. We treat recognition in a nearest-neighbor classification framework. Results are presented for silhouettes, trademarks, handwritten digits and the COIL dataset.
Matching shapes
Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001 ; 1 ; 454-461 vol.1
2001-01-01
768889 byte
Conference paper
Electronic Resource
English
British Library Conference Proceedings | 2001
|Representation and Matching of Articulated Shapes
British Library Conference Proceedings | 2004
|Representation and matching of articulated shapes
IEEE | 2004
|Optimal matching between shapes via elastic deformations
British Library Online Contents | 1999
|Robust Point Matching for Two-Dimensional Nonrigid Shapes
British Library Conference Proceedings | 2005
|