Flexible syntactic matching of curves and its application to automatic hierarchical classification of silhouettes
- 1 January 1999
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 21 (12) , 1312-1328
- https://doi.org/10.1109/34.817410
Abstract
Curve matching is one instance of the fundamental correspondence problem. Our flexible algorithm is designed to match curves under substantial deformations and arbitrary large scaling and rigid transformations. A syntactic representation is constructed for both curves and an edit transformation which maps one curve to the other is found using dynamic programming. We present extensive experiments where we apply the algorithm to silhouette matching. In these experiments, we examine partial occlusion, viewpoint variation, articulation, and class matching (where silhouettes of similar objects are matched). Based on the qualitative syntactic matching, we define a dissimilarity measure and we compute it for every pair of images in a database of 121 images. We use this experiment to objectively evaluate our algorithm: First, we compare our results to those reported by others. Second, we use the dissimilarity values in order to organize the image database into shape categories. The veridical hierarchical organization stands as evidence to the quality of our matching and similarity estimation.Keywords
This publication has 45 references indexed in Scilit:
- On view likelihood and stabilityPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1997
- Similarity and affine invariant distances between 2D point setsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1995
- Shape matching using polygon approximation and dynamic alignmentPattern Recognition Letters, 1993
- Computation of normalized edit distance and applicationsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1993
- Learning visual models from shape contours using multiscale convex/concave structure matchingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1993
- Parameterized point pattern matching and its application to recognition of object familiesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1993
- Matching: Invariant to translations, rotations and scale changesPattern Recognition, 1992
- Affine invariant model-based object recognitionIEEE Transactions on Robotics and Automation, 1990
- Optimal correspondence of string subsequencesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1990
- Features of similarity.Psychological Review, 1977