Advertisement

2D → 2D geometric transformation invariant to arbitrary translations, rotations and scales

  • Lucian Muresan
Invariants
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1296)

Abstract

This paper presents a geometric transformation invariant to arbitrary translations, rotations and scales changes. The output contains only intrinsic information on the internal structure of pattern consisting of pairs of angles. This approach does not use specific feature points of the curve as curvature maxima, torsion extrema or curvature discontinuity. The quasi-linearity feature of this transformation allows recognition of two or more images without segmentation. It also allows the reconstruction of image when a part of it is missing or the recognition when extra noise curves are on the same scene.

Keywords

Invariant Representation Input Pattern Geometric Transformation Input Curve Visual Pattern Recognition 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Li,S.Z.: Matching: Invariant to Translations, Rotations and Scale Changes. Pattern Recognition bf 25 (1992) 583–594CrossRefGoogle Scholar
  2. 2.
    Li,S.Z.: Invariant Representation, Matching and Pose Estimation of 3D Space Curves under Similarity Transformations. Preprint Pattern Recognition accepted for publication (1996)Google Scholar
  3. 3.
    Carlsson,S.: Combinatorial Geometry for Shape Representation and Indexing. Proc. International Workshop on Object Representation for Computer Vision (1996) April 13–14 Cambrige England.Google Scholar
  4. 4.
    Carlsson,S: View Variation and Linear Invariants in 2D and 3D. Tech. rep. Royal Institute of Technology (1995)Google Scholar
  5. 5.
    Bruckstein, A.M., Rivlin, E. and Weiss,L: Scale Space Local Invariants CIS Report 9503, Technion-Israel Institute Of Technology (1995)Google Scholar
  6. 6.
    Bruckstein, A.M., Holt, R.J., Netravali, A.N. and Richardson, T.J.: Invariant Signatures for Planar Shape Recognition under Partial Occlusion CVCIP: Image Understanding 58 (1993) 49–65Google Scholar
  7. 7.
    Mundy, J.L., Zisserman, A. and Forsyth, D. (eds.): Applications of Invariance in Computer Vision Lecture Notes in Computer Science Springer-Verlag 825 (1994)Google Scholar
  8. 8.
    Maybank, S.J.: Relation Between 3D Invariants and 2D Invariants Proc. IEEE Workshop on Representation of Visual Scenes MIT, Cambrige, MA. June 24 (1995)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • Lucian Muresan
    • 1
  1. 1.JINRzDubna, Moscow RegionRussia

Personalised recommendations