ML Anthology

A Variational Approach to the Evolution of Radial Basis Functions for Image Segmentation

Greg G. Slabaugh, Huong Quynh Dinh, Gozde B. Unal
CVPR 2007
doi:10.1109/CVPR.2007.383013 /cvpr/2007/slabaugh2007cvpr-variational/

Abstract

In this paper we derive differential equations for evolving radial basis functions (RBFs) to solve segmentation problems. The differential equations result from applying variational calculus to energy functionals designed for image segmentation. Our methodology supports evolution of all parameters of each RBF, including its position, weight, orientation, and anisotropy, if present. Our framework is general and can be applied to numerous RBF interpolants. The resulting approach retains some of the ideal features of implicit active contours, like topological adaptivity, while requiring low storage overhead due to the sparsity of our representation, which is an unstructured list of RBFs. We present the theory behind our technique and demonstrate its usefulness for image segmentation.

PDF CVPR Semantic Scholar

Cite

Text

Slabaugh et al. "A Variational Approach to the Evolution of Radial Basis Functions for Image Segmentation." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2007. doi:10.1109/CVPR.2007.383013

Markdown

[Slabaugh et al. "A Variational Approach to the Evolution of Radial Basis Functions for Image Segmentation." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2007.](https://mlanthology.org/cvpr/2007/slabaugh2007cvpr-variational/) doi:10.1109/CVPR.2007.383013

BibTeX

@inproceedings{slabaugh2007cvpr-variational,
  title     = {{A Variational Approach to the Evolution of Radial Basis Functions for Image Segmentation}},
  author    = {Slabaugh, Greg G. and Dinh, Huong Quynh and Unal, Gozde B.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2007},
  doi       = {10.1109/CVPR.2007.383013},
  url       = {https://mlanthology.org/cvpr/2007/slabaugh2007cvpr-variational/}
}