Regularized Partial Matching of Rigid Shapes

Abstract

Matching of rigid shapes is an important problem in numerous applications across the boundary of computer vision, pattern recognition and computer graphics communities. A particularly challenging setting of this problem is partial matching, where the two shapes are dissimilar in general, but have significant similar parts. In this paper, we show a rigorous approach allowing to find matching parts of rigid shapes with controllable size and regularity. The regularity term we use is similar to the spirit of the Mumford-Shah functional, extended to non-Euclidean spaces. Numerical experiments show that the regularized partial matching produces better results compared to the non-regularized one.

Cite

Text

Bronstein and Bronstein. "Regularized Partial Matching of Rigid Shapes." European Conference on Computer Vision, 2008. doi:10.1007/978-3-540-88688-4_11

Markdown

[Bronstein and Bronstein. "Regularized Partial Matching of Rigid Shapes." European Conference on Computer Vision, 2008.](https://mlanthology.org/eccv/2008/bronstein2008eccv-regularized/) doi:10.1007/978-3-540-88688-4_11

BibTeX

@inproceedings{bronstein2008eccv-regularized,
  title     = {{Regularized Partial Matching of Rigid Shapes}},
  author    = {Bronstein, Alexander M. and Bronstein, Michael M.},
  booktitle = {European Conference on Computer Vision},
  year      = {2008},
  pages     = {143-154},
  doi       = {10.1007/978-3-540-88688-4_11},
  url       = {https://mlanthology.org/eccv/2008/bronstein2008eccv-regularized/}
}