A new technique for local symmetry estimation

Authors:
Matthew Mellor;Michael Brady
Affiliations:
Medical Vision Laboratory, University of Oxford, UK;Medical Vision Laboratory, University of Oxford, UK
Venue:
Scale-Space'05 Proceedings of the 5th international conference on Scale Space and PDE Methods in Computer Vision
Year:
2005

Citing 4
Cited 3

The Design and Use of Steerable Filters

IEEE Transactions on Pattern Analysis and Machine Intelligence
The multiscale medial axis and its applications in image registration

VIP '94 The international conference on volume image processing on Volume image processing
Untangling the Blum Medial Axis Transform

International Journal of Computer Vision - Special Issue on Research at the University of North Carolina Medical Image Display Analysis Group (MIDAG)
The monogenic signal

IEEE Transactions on Signal Processing

Radial symmetries based decomposition of cell clusters in binary and gray level images

Pattern Recognition
Symmetries of 2-D Images: Cases without Periodic Translations

Journal of Mathematical Imaging and Vision
Basic Image Features (BIFs) Arising from Approximate Symmetry Type

SSVM '09 Proceedings of the Second International Conference on Scale Space and Variational Methods in Computer Vision

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper introduces a new approach to symmetry estimation directly from image grey values. The method was inspired by the local phase based method, proposed by Kovesi. This method is examined in the light of a strict definition of local symmetry, and found to be wanting in two respects: that it is invariant to some apparently non-trivial symmetries and that its scale is ill defined. To avoid these difficulties we propose a non-linear analog of the local phase. This leads to a family of local symmetry measures, able to provide a rich, local characterisation of shape, invariant to rotations and affine intensity transformations, and robust to affine coordinate transformations.