Scale Space Semi-local Invariants
Scale space semi-local invariants.
Image Vision Comput., 15(5):335-344, 1997
Online Version
A pdf version is available for download.
Abstract
In this paper we discuss a new approach to invariant signatures for recognizing curves under viewing distortions and partial occlusion. The approach is intended to overcome the ill-posed problem of finding derivatives, on which local invariants usually depend. The basic idea is to use invariant finite differences, with a scale parameter that determines the size of the differencing interval. The scale parameter is allowed to vary so that we obtain a ‘scale space'-like invariant representation of the curve, with larger difference intervals corresponding to larger, coarser scales. In this new representation, each traditional local invariant is replaced by a scale-dependent range of invariants. Thus, instead of invariant signature curves we obtain invariant signature surfaces in a 3-D Invariant ‘scale space'.
Keywords
Co-authors
Bibtex Entry
@article{BrucksteinRW97a,
title = {Scale space semi-local invariants.},
author = {Alfred M. Bruckstein and Ehud Rivlin and Isaac Weiss},
year = {1997},
journal = {Image Vision Comput.},
volume = {15},
number = {5},
pages = {335-344},
keywords = {Invariants; Object recognition; Scale space},
abstract = {In this paper we discuss a new approach to invariant signatures for recognizing curves under viewing distortions and partial occlusion. The approach is intended to overcome the ill-posed problem of finding derivatives, on which local invariants usually depend. The basic idea is to use invariant finite differences, with a scale parameter that determines the size of the differencing interval. The scale parameter is allowed to vary so that we obtain a ‘scale space'-like invariant representation of the curve, with larger difference intervals corresponding to larger, coarser scales. In this new representation, each traditional local invariant is replaced by a scale-dependent range of invariants. Thus, instead of invariant signature curves we obtain invariant signature surfaces in a 3-D Invariant ‘scale space'.}
}