1 Low-level Feature Detection Using the Boundary Tensor

@inproceedings{Kthe1LF,
  title={1 Low-level Feature Detection Using the Boundary Tensor},
  author={Ullrich K{\"o}the}
}
Tensors are a useful tool for the detection of low-level features such as edges, lines, corners, and junctions because they can represent feature strength and orientation in a way that is easy to work with. However, traditional approaches to define feature tensors have a number of disadvantages. By means of the first and second order Riesz transforms, we propose a new approach called the boundary tensor. Using quadratic convolution equations, we show that the boundary tensor overcomes some… CONTINUE READING

Citations

Publications citing this paper.
Showing 1-9 of 9 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 14 references

A Feature Based Correspondence Algorithm for Image Matching, Intl

  • W. Förstner
  • Arch. of Photogrammetry and Remote Sensing,
  • 1986
Highly Influential
5 Excerpts

Stevens: A Combined Corner and Edge Detector

  • M.J.C.G. Harris
  • Proc. of 4th Alvey Vision Conference,
  • 1988
Highly Influential
3 Excerpts

Farnebäck: A Framework for Estimation of Orientation and Velocity

  • G. K. Nordberg
  • Proc. IEEE Intl. Conf. on Image Processing,
  • 2003
3 Excerpts

Sicuranza : Quadratic Filters for Signal Processing

  • G.
  • Proc . IEEE Intl . Conf . on Image Processing
  • 2003

Förstner : A Feature Based Correspondence Algorithm for Image Matching

  • W.
  • The Monogenic Signal , IEEE Trans . Image…
  • 2001

Quadratic Filters for Signal Processing

  • G. Sicuranza
  • Proc. of the IEEE,
  • 1992
1 Excerpt

Similar Papers

Loading similar papers…