Shape matching and object recognition using shape contexts
Top Cited Papers
- 7 August 2002
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 24 (4) , 509-522
- https://doi.org/10.1109/34.993558
Abstract
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. The dissimilarity between the 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 as the problem of finding the stored prototype shape that is maximally similar to that in the image. Results are presented for silhouettes, trademarks, handwritten digits, and the COIL data set.Keywords
This publication has 47 references indexed in Scilit:
- Matching shapesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Shape matching and object recognition using shape contextsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Order Structure, Correspondence, and Shape Based CategoriesPublished by Springer Nature ,1999
- A bootstrapping algorithm for learning linear models of object classesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1997
- Joint induction of shape features and tree classifiersPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1997
- Support-vector networksMachine Learning, 1995
- Active Shape Models-Their Training and ApplicationComputer Vision and Image Understanding, 1995
- Principal warps: thin-plate splines and the decomposition of deformationsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1989
- Splines minimizing rotation-invariant semi-norms in Sobolev spacesPublished by Springer Nature ,1977
- A Distribution Free Version of the Smirnov Two Sample Test in the $p$-Variate CaseThe Annals of Mathematical Statistics, 1969