Representation and Detection of Deformable Shapes

Felzenszwalb, Pedro F.

doi:10.1109/CVPR.2003.1211343

Representation and Detection of Deformable Shapes

Pedro F. Felzenszwalb

CVPR 2003 pp. 102-108

doi:10.1109/CVPR.2003.1211343 /cvpr/2003/felzenszwalb2003cvpr-representation/

Abstract

We present a method for detecting deformable shapes in images. The main difficulty with deformable template models is the very large (or infinite) number of possible nonrigid transformations of the templates. This makes the problem of finding an optimal match of a deformable template to an image incredibly hard. Using a new representation for deformable shapes we show how to efficiently find a global optimal solution to the nonrigid matching problem. Our matching algorithm can minimize a large class of energy functions, making it applicable to a wide range of problems. We present experimental results of detecting shapes in medical and natural images. Because we do not rely on local search techniques, our method is very robust, yielding good matches even in images with high clutter.

PDF CVPR Semantic Scholar

Cite

Text

Felzenszwalb. "Representation and Detection of Deformable Shapes." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2003. doi:10.1109/CVPR.2003.1211343

Markdown

[Felzenszwalb. "Representation and Detection of Deformable Shapes." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2003.](https://mlanthology.org/cvpr/2003/felzenszwalb2003cvpr-representation/) doi:10.1109/CVPR.2003.1211343

BibTeX

@inproceedings{felzenszwalb2003cvpr-representation,
  title     = {{Representation and Detection of Deformable Shapes}},
  author    = {Felzenszwalb, Pedro F.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2003},
  pages     = {102-108},
  doi       = {10.1109/CVPR.2003.1211343},
  url       = {https://mlanthology.org/cvpr/2003/felzenszwalb2003cvpr-representation/}
}