ML Anthology

Elastic-String Models for Representation and Analysis of Planar Shapes

Washington Mio, Anuj Srivastava
CVPR 2004 pp. 10-15
doi:10.1109/CVPR.2004.93 /cvpr/2004/mio2004cvpr-elastic/

Abstract

We develop a new framework for the quantitative analysis of shapes of planar curves. Shapes are modeled on elastic strings that can be bent, stretched or compressed at different rates along the curve. Shapes are treated as elements of a space obtained as the quotient of an infinite-dimensional Riemannian manifold of elastic curves by the action of a reparameterization group. The Riemannian metric encodes the elastic properties of the string and has the property that reparameterizations act by isometrics. The geodesies in shape space are used to quantify shape dissimilarities, interpolate and extrapolate shapes, and align shapes according to their elastic properties. The shape spaces and metrics constructed offer a novel environment for the study of shape statistics and for the investigation and simulation of shape dynamics.

CVPR Semantic Scholar

Cite

Text

Mio and Srivastava. "Elastic-String Models for Representation and Analysis of Planar Shapes." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2004. doi:10.1109/CVPR.2004.93

Markdown

[Mio and Srivastava. "Elastic-String Models for Representation and Analysis of Planar Shapes." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2004.](https://mlanthology.org/cvpr/2004/mio2004cvpr-elastic/) doi:10.1109/CVPR.2004.93

BibTeX

@inproceedings{mio2004cvpr-elastic,
  title     = {{Elastic-String Models for Representation and Analysis of Planar Shapes}},
  author    = {Mio, Washington and Srivastava, Anuj},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2004},
  pages     = {10-15},
  doi       = {10.1109/CVPR.2004.93},
  url       = {https://mlanthology.org/cvpr/2004/mio2004cvpr-elastic/}
}