ML Anthology

Efficient Tensor Voting with 3D Tensorial Harmonics

Marco Reisert, Hans Burkhardt
CVPRW 2008 pp. 1-7
doi:10.1109/CVPRW.2008.4562962 /cvprw/2008/reisert2008cvprw-efficient/

Abstract

Tensor voting is a robust technique to extract low-level features in noisy images. The approach achieves its robustness by exploiting coherent orientations in local neighborhoods. In this paper we propose an efficient algorithm for dense tensor voting in 3D which makes use of steerable filters. Therefore, we propose steerable expansions of spherical tensor fields in terms of tensorial harmonics, which are their canonical representation. In this way it is possible to perform arbitrary rank tensor voting by linear-combinations of convolutions in an efficient way.

PDF CVPRW Semantic Scholar

Cite

Text

Reisert and Burkhardt. "Efficient Tensor Voting with 3D Tensorial Harmonics." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2008. doi:10.1109/CVPRW.2008.4562962

Markdown

[Reisert and Burkhardt. "Efficient Tensor Voting with 3D Tensorial Harmonics." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2008.](https://mlanthology.org/cvprw/2008/reisert2008cvprw-efficient/) doi:10.1109/CVPRW.2008.4562962

BibTeX

@inproceedings{reisert2008cvprw-efficient,
  title     = {{Efficient Tensor Voting with 3D Tensorial Harmonics}},
  author    = {Reisert, Marco and Burkhardt, Hans},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2008},
  pages     = {1-7},
  doi       = {10.1109/CVPRW.2008.4562962},
  url       = {https://mlanthology.org/cvprw/2008/reisert2008cvprw-efficient/}
}