ML Anthology

Parametrically Deformable Contour Models

Lawrence H. Staib, James S. Duncan
CVPR 1989 pp. 98-103
doi:10.1109/CVPR.1989.37834 /cvpr/1989/staib1989cvpr-parametrically/

Abstract

Segmentation using boundary finding is enhanced both by considering the boundary as a whole and by using model-based shape information. Flexible constraints, in the form of a probabilistic deformable model, are applied to the problem of segmenting natural objects whose diversity and irregularity of shape makes them poorly represented in terms of fixed features of forms. The parametric model is based on the elliptic Fourier decomposition of the boundary. The segmentation problem is solved as an optimization problem, where the best match between the boundary (as defined by the parameter vector) and the image data is found. Initial experimentation shows good results on a variety of images.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

CVPR Semantic Scholar

Cite

Text

Staib and Duncan. "Parametrically Deformable Contour Models." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1989. doi:10.1109/CVPR.1989.37834

Markdown

[Staib and Duncan. "Parametrically Deformable Contour Models." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1989.](https://mlanthology.org/cvpr/1989/staib1989cvpr-parametrically/) doi:10.1109/CVPR.1989.37834

BibTeX

@inproceedings{staib1989cvpr-parametrically,
  title     = {{Parametrically Deformable Contour Models}},
  author    = {Staib, Lawrence H. and Duncan, James S.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1989},
  pages     = {98-103},
  doi       = {10.1109/CVPR.1989.37834},
  url       = {https://mlanthology.org/cvpr/1989/staib1989cvpr-parametrically/}
}