Hierarchical Matching of Deformable Shapes

Felzenszwalb, Pedro F.; Schwartz, Joshua D.

doi:10.1109/CVPR.2007.383018

Hierarchical Matching of Deformable Shapes

Pedro F. Felzenszwalb, Joshua D. Schwartz

CVPR 2007

doi:10.1109/CVPR.2007.383018 /cvpr/2007/felzenszwalb2007cvpr-hierarchical/

Abstract

We describe a new hierarchical representation for two-dimensional objects that captures shape information at multiple levels of resolution. This representation is based on a hierarchical description of an object's boundary and can be used in an elastic matching framework, both for comparing pairs of objects and for detecting objects in cluttered images. In contrast to classical elastic models, our representation explicitly captures global shape information. This leads to richer geometric models and more accurate recognition results. Our experiments demonstrate classification results that are significantly better than the current state-of-the-art in several shape datasets. We also show initial experiments in matching shapes to cluttered images.

PDF CVPR Semantic Scholar

Cite

Text

Felzenszwalb and Schwartz. "Hierarchical Matching of Deformable Shapes." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2007. doi:10.1109/CVPR.2007.383018

Markdown

[Felzenszwalb and Schwartz. "Hierarchical Matching of Deformable Shapes." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2007.](https://mlanthology.org/cvpr/2007/felzenszwalb2007cvpr-hierarchical/) doi:10.1109/CVPR.2007.383018

BibTeX

@inproceedings{felzenszwalb2007cvpr-hierarchical,
  title     = {{Hierarchical Matching of Deformable Shapes}},
  author    = {Felzenszwalb, Pedro F. and Schwartz, Joshua D.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2007},
  doi       = {10.1109/CVPR.2007.383018},
  url       = {https://mlanthology.org/cvpr/2007/felzenszwalb2007cvpr-hierarchical/}
}