Advanced

Affine and Projective Normalization of Planar Curves and Regions

Åström, Karl LU (1994) Proceedings of Third European Conference on Computer Vision, Volume II In Computer Vision ECCV'94 2. p.439-448
Abstract
Recent research has shown that invariant indexing can speed up the recognition process in computer vision. Extraction of invariant features can be done by choosing first a canonical reference frame, and then features in this reference frame. This paper gives methods for extracting invariants for planar curves under affine and projective transformations. The invariants can be used semilocally to recognize occluded objects. For affine transformations, there are methods giving a unique reference frame, with continuity in the Hausdorff metric. This is not possible in the projective case. Continuity can, however, be kept by sacrificing uniqueness
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
Recognition, planar curves, projective and affine invariants, computational geometry, computer vision
in
Computer Vision ECCV'94
editor
Eklundh, Jan-Olof
volume
2
pages
439 - 448
publisher
Springer
conference name
Proceedings of Third European Conference on Computer Vision, Volume II
ISBN
3 540 57957 5
language
English
LU publication?
yes
id
50553a62-9c97-49a2-9742-798e55d1b030 (old id 787633)
date added to LUP
2008-03-31 14:56:14
date last changed
2016-04-16 09:46:41
@misc{50553a62-9c97-49a2-9742-798e55d1b030,
  abstract     = {Recent research has shown that invariant indexing can speed up the recognition process in computer vision. Extraction of invariant features can be done by choosing first a canonical reference frame, and then features in this reference frame. This paper gives methods for extracting invariants for planar curves under affine and projective transformations. The invariants can be used semilocally to recognize occluded objects. For affine transformations, there are methods giving a unique reference frame, with continuity in the Hausdorff metric. This is not possible in the projective case. Continuity can, however, be kept by sacrificing uniqueness},
  author       = {Åström, Karl},
  editor       = {Eklundh, Jan-Olof},
  isbn         = {3 540 57957 5},
  keyword      = {Recognition,planar curves,projective and affine invariants,computational geometry,computer vision},
  language     = {eng},
  pages        = {439--448},
  publisher    = {ARRAY(0x90c23e8)},
  series       = {Computer Vision ECCV'94},
  title        = {Affine and Projective Normalization of Planar Curves and Regions},
  volume       = {2},
  year         = {1994},
}