Interesting Patterns for Model-Based Machine Vision

Abstract

The author's work builds on D.G. Lowe's (1987) theory of perceptual groupings. Minimal processing is applied to an image to extract edges. The edges are then represented as well-defined two-dimensional patterns that the authors call interesting patterns. No attempt is made to infer three-dimensional structure from the patterns, and they are matched against two-dimensional models which are projections of characteristic views of three-dimensional objects. The patterns are built up from modular building blocks called triples.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

Cite

Text

Henikoff and Shapiro. "Interesting Patterns for Model-Based Machine Vision." IEEE/CVF International Conference on Computer Vision, 1990. doi:10.1109/ICCV.1990.139590

Markdown

[Henikoff and Shapiro. "Interesting Patterns for Model-Based Machine Vision." IEEE/CVF International Conference on Computer Vision, 1990.](https://mlanthology.org/iccv/1990/henikoff1990iccv-interesting/) doi:10.1109/ICCV.1990.139590

BibTeX

@inproceedings{henikoff1990iccv-interesting,
  title     = {{Interesting Patterns for Model-Based Machine Vision}},
  author    = {Henikoff, Jorja G. and Shapiro, Linda G.},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {1990},
  pages     = {535-538},
  doi       = {10.1109/ICCV.1990.139590},
  url       = {https://mlanthology.org/iccv/1990/henikoff1990iccv-interesting/}
}