• TUCS Publication Series
• How to Publish in TUCS Series
• Publication Search
• Publication Graph
• Publication Input
• Publication Input Guide
• JuFo Browser

A Shape-Preserving Non-Parametric Symmetry Transform

Olli Lahdenoja, Esa Alhoniemi, Mika Laiho, Ari Paasio, A Shape-Preserving Non-Parametric Symmetry Transform. In: IEEE 18th Intenational Conference on Pattern Recognition (ICPR 2006), 2, 373-377, IEEE, 2006.

Abstract:

Recently, a non-parametric image measure, symmetry, for local binary
patterns has been introduced. In this paper, we propose a generalised
symmetry transform for arbitrary neighbourhoods and describe its
theoretical properties. The symmetry of the local binary patterns is
shown to be a special case of a more general non-parametric concept.
Applications of the symmetry include searching of interest points and
correspondence.

BibTeX entry:

@INPROCEEDINGS{inpLaAlLaPa06a,
  title = {A Shape-Preserving Non-Parametric Symmetry Transform},
  booktitle = {IEEE 18th Intenational Conference on Pattern Recognition (ICPR 2006)},
  author = {Lahdenoja, Olli and Alhoniemi, Esa and Laiho, Mika and Paasio, Ari},
  volume = {2},
  publisher = {IEEE},
  pages = {373-377},
  year = {2006},
}

Belongs to TUCS Research Unit(s): Algorithmics and Computational Intelligence Group (ACI), Microelectronics

Edit publication