Advanced

An affine invariant deformable shape representation for general curves

Ericsson, Anders LU and Åström, Karl LU (2003) 9th International Conference on Computer Vision, IEEE In Proceedings of the IEEE International Conference on Computer Vision 2. p.1142-1149
Abstract
Automatic construction of Shape Models from examples has been the focus of intense research during the last couple of years. These methods have proved to be useful for shape segmentation, tracking and shape understanding. In this paper novel theory to automate shape modelling is described. The theory is intrinsically defined for curves although curves are infinite dimensional objects. The theory is independent of parameterisation and affine transformations. We suggest a method for implementing the ideas and compare it to minimising the Description Length of the model (MDL). It turns out that the accuracy of the two methods is comparable. Both the MDL and our approach can get Stuck at local minima. Our algorithm is less computational... (More)
Automatic construction of Shape Models from examples has been the focus of intense research during the last couple of years. These methods have proved to be useful for shape segmentation, tracking and shape understanding. In this paper novel theory to automate shape modelling is described. The theory is intrinsically defined for curves although curves are infinite dimensional objects. The theory is independent of parameterisation and affine transformations. We suggest a method for implementing the ideas and compare it to minimising the Description Length of the model (MDL). It turns out that the accuracy of the two methods is comparable. Both the MDL and our approach can get Stuck at local minima. Our algorithm is less computational expensive and relatively good solutions are obtained after a few iterations. The MDL is, however, better suited at fine-tuning the parameters given good initial estimates to the problem. It is shown that a combination of the two methods outperforms either on its own. (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
Affine invariant deformable shape representation, Description length of the model, Shape variation
in
Proceedings of the IEEE International Conference on Computer Vision
volume
2
pages
1142 - 1149
publisher
IEEE--Institute of Electrical and Electronics Engineers Inc.
conference name
9th International Conference on Computer Vision, IEEE
external identifiers
  • wos:000186833000151
  • other:CODEN: PICVES
  • scopus:0344983282
ISBN
0-7695-1950-4
DOI
10.1109/ICCV.2003.1238477
language
English
LU publication?
yes
id
d764c238-f561-4daf-881b-205922a2f3fb (old id 612789)
date added to LUP
2007-11-28 12:51:37
date last changed
2017-01-01 08:05:22
@inproceedings{d764c238-f561-4daf-881b-205922a2f3fb,
  abstract     = {Automatic construction of Shape Models from examples has been the focus of intense research during the last couple of years. These methods have proved to be useful for shape segmentation, tracking and shape understanding. In this paper novel theory to automate shape modelling is described. The theory is intrinsically defined for curves although curves are infinite dimensional objects. The theory is independent of parameterisation and affine transformations. We suggest a method for implementing the ideas and compare it to minimising the Description Length of the model (MDL). It turns out that the accuracy of the two methods is comparable. Both the MDL and our approach can get Stuck at local minima. Our algorithm is less computational expensive and relatively good solutions are obtained after a few iterations. The MDL is, however, better suited at fine-tuning the parameters given good initial estimates to the problem. It is shown that a combination of the two methods outperforms either on its own.},
  author       = {Ericsson, Anders and Åström, Karl},
  booktitle    = {Proceedings of the IEEE International Conference on Computer Vision},
  isbn         = {0-7695-1950-4},
  keyword      = {Affine invariant deformable shape representation,Description length of the model,Shape variation},
  language     = {eng},
  pages        = {1142--1149},
  publisher    = {IEEE--Institute of Electrical and Electronics Engineers Inc.},
  title        = {An affine invariant deformable shape representation for general curves},
  url          = {http://dx.doi.org/10.1109/ICCV.2003.1238477},
  volume       = {2},
  year         = {2003},
}