Multi-Scale, Torsion-Based Shape Representations for Space Curves

Mokhtarian, Farzin

doi:10.1109/CVPR.1993.341040

Multi-Scale, Torsion-Based Shape Representations for Space Curves

Farzin Mokhtarian

CVPR 1993 pp. 660-661

doi:10.1109/CVPR.1993.341040 /cvpr/1993/mokhtarian1993cvpr-multi/

Abstract

Space curves are efficient, highly descriptive features of 3-D objects. A new multiscale shape representation (the resampled torsion scale space or TSS image) for space curves suitable for recognition of a noisy curve at any scale or orientation is introduced. A two-phase matching algorithm consisting of TSS matching (using extrema of TSS zero-crossing contours) followed by transformation parameter optimization demonstrates the usefulness of the representation in recognition tasks.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>

CVPR Semantic Scholar

Cite

Text

Mokhtarian. "Multi-Scale, Torsion-Based Shape Representations for Space Curves." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1993. doi:10.1109/CVPR.1993.341040

Markdown

[Mokhtarian. "Multi-Scale, Torsion-Based Shape Representations for Space Curves." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1993.](https://mlanthology.org/cvpr/1993/mokhtarian1993cvpr-multi/) doi:10.1109/CVPR.1993.341040

BibTeX

@inproceedings{mokhtarian1993cvpr-multi,
  title     = {{Multi-Scale, Torsion-Based Shape Representations for Space Curves}},
  author    = {Mokhtarian, Farzin},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1993},
  pages     = {660-661},
  doi       = {10.1109/CVPR.1993.341040},
  url       = {https://mlanthology.org/cvpr/1993/mokhtarian1993cvpr-multi/}
}