ML Anthology

Shock Graphs and Shape Matching

Kaleem Siddiqi, Ali Shokoufandeh, Sven J. Dickinson, Steven W. Zucker
ICCV 1998 pp. 222-229
doi:10.1109/ICCV.1998.710722 /iccv/1998/siddiqi1998iccv-shock/

Abstract

We have been developing a theory for the generic representation of 2-0 shape, where structural descrip-tions are derived from the shocks (singularities) of a curve evolution process, acting on bounding contours. We now apply the theory to the problem of shape match-ing. The shocks are organized into a directed, acyclic shock graph, and complexity is managed by attending to the most significant (central) shape components first. The space of all such graphs is highly structured and can be characterized by the rules of a shock graph gram-mar. The grammar permits a reduction of a shock graph to a unique rooted shock tree. We introduce a novel tree matching algorithm which finds the best set of corresponding nodes between two shock trees an poly-nomial time. Using a diverse database of shapes, we demonstrate our system’s performance under articula-tion, occlusion, and changes in viewpoint. 1

ICCV Semantic Scholar

Cite

Text

Siddiqi et al. "Shock Graphs and Shape Matching." IEEE/CVF International Conference on Computer Vision, 1998. doi:10.1109/ICCV.1998.710722

Markdown

[Siddiqi et al. "Shock Graphs and Shape Matching." IEEE/CVF International Conference on Computer Vision, 1998.](https://mlanthology.org/iccv/1998/siddiqi1998iccv-shock/) doi:10.1109/ICCV.1998.710722

BibTeX

@inproceedings{siddiqi1998iccv-shock,
  title     = {{Shock Graphs and Shape Matching}},
  author    = {Siddiqi, Kaleem and Shokoufandeh, Ali and Dickinson, Sven J. and Zucker, Steven W.},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {1998},
  pages     = {222-229},
  doi       = {10.1109/ICCV.1998.710722},
  url       = {https://mlanthology.org/iccv/1998/siddiqi1998iccv-shock/}
}