ML Anthology

Nonlinear Phase Portrait Models for Oriented Textures

Ralph M. Ford, Robin N. Strickland
CVPR 1993 pp. 644-645
doi:10.1109/CVPR.1993.341047 /cvpr/1993/ford1993cvpr-nonlinear/

Abstract

Nonlinear differential equations in Taylor series form are employed to model oriented textures. These models build upon the linear phase portrait description. Inclusion of higher order nonlinear terms provides a more accurate description in critical point regions. Nonlinear models containing multiple critical points are generated from linear phase portrait descriptions. The resulting models are highly compact descriptors, in that the flow-like textures of complex patterns are described by a single nonlinear system of differential equations.< <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

Ford and Strickland. "Nonlinear Phase Portrait Models for Oriented Textures." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1993. doi:10.1109/CVPR.1993.341047

Markdown

[Ford and Strickland. "Nonlinear Phase Portrait Models for Oriented Textures." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1993.](https://mlanthology.org/cvpr/1993/ford1993cvpr-nonlinear/) doi:10.1109/CVPR.1993.341047

BibTeX

@inproceedings{ford1993cvpr-nonlinear,
  title     = {{Nonlinear Phase Portrait Models for Oriented Textures}},
  author    = {Ford, Ralph M. and Strickland, Robin N.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1993},
  pages     = {644-645},
  doi       = {10.1109/CVPR.1993.341047},
  url       = {https://mlanthology.org/cvpr/1993/ford1993cvpr-nonlinear/}
}