Affine and projective normalization of planar curves and regions

  • Kalle åström
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 801)


Recent research has showed 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.


Recognition planar curves projective and affine invariants 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [BM1]
    Blake, A., Marinos, C.: Shape from Texture: Estimation, Isotropy and Moments. Artificial Intelligence 45 (1990) 332–380Google Scholar
  2. [BS1]
    Blake, A., Sinclair, D.: On the projective normalisation of planar shape. Technical Report OUEL Oxford Great Britain (1992)Google Scholar
  3. [BY1]
    Brady, M., Yuille, A.: An Extremum Principle for Shape from Contour. PAMI-6 3 (1984) 288–301Google Scholar
  4. [BW1]
    Burns J. B., Weiss R. S., Riseman E. M.: The Non-existence of General-case View-Invariants, in Geometrical Invariance in Computer Vision, Mundy, J. L. and Zisserman, A. editors, MIT Press (1992) 120–131Google Scholar
  5. [Ca1]
    Carlsson S.: Projectively Invariant Decomposition and Recognition of Planar Shapes, Proc. ICCV4, May, Berlin, Germany (1993) 471–475Google Scholar
  6. [DH1]
    Duda, R. O. and Hart, P. E.: Pattern Classification and Scene Analysis. Wiley-Interscience (1973)Google Scholar
  7. [GM1]
    Van Gool, L., Moons, T., Pauwels, E. and Oosterlinck, A.: Semi-differential Invariants. in Geometrical Invariance in Computer Vision, Mundy, J. L. and Zisserman, A. editors, MIT Press (1992) 157–192Google Scholar
  8. [Gå1]
    Gårding, J.: Shape from Surface Markings. Ph. D. thesis, Dept. of Numerical Analysis and Computer Science, Royal Institute of Technology, Stockholm, Sweden (1991)Google Scholar
  9. [G1]
    Gros, P., and Quan L.: Projective Invariants for Vision. Technical Report RT 90 IMAG — 15 LIFIA, LIFIA-IRIMAG, Grenoble, France (1992)Google Scholar
  10. [LS1]
    Lamdan, Y., Schwartz, J. T., and Wolfson, H. J.: Affine Invariant Model-based Object Recognition. IEEE Journal of Robotics and Automation 6 (1990) 578–589Google Scholar
  11. [MZ1]
    Mundy, J. L., and Zisserman A. (editors): Geometric invariance in Computer Vision. MIT Press, Cambridge Ma, USA (1990)Google Scholar
  12. [RZ1]
    Rothwell, C. A., Zisserman, A., Forsyth, D. A. and Mundy J. L.: Canonical Frames for Planar Object Recognition. Proc. ECCV92 Genova Italy (1992) 757–772Google Scholar
  13. [Ro1]
    Rothwell, C. A.: Hierarchical Object Description Using Invariants. Proc. Second ARPA/NSF-ESPRIT Workshop on Invariance, Ponta Delgada, Azores (1993) 287–302Google Scholar
  14. [We1]
    Weiss, I.: Noise-resistant Invariants of Curves. in Geometrical Invariance in Computer Vision, Mundy, J. L. and Zisserman, A. editors, MIT Press (1992) 135–156Google Scholar
  15. [Wi1]
    Witkin, A. P.: Recovering Surface Shape and Orientation from Texture. J. of Artificial Intelligence 17 (1981) 17–45Google Scholar
  16. [ås1]
    åström, K.: A Correspondence Problem in Laser-Guided Navigation. Proc. Swedish Society for Automated Image Analysis, Uppsala, Sweden (1992) 141–144Google Scholar
  17. [ås2]
    åström, K.: Affine Invariants of Planar Sets. Proc. SCIA8, Tromsö, Norway (1993) 769–776Google Scholar
  18. [ås3]
    åström, K.: Fundamental Difficulties with Projective Normalization of Planar Curves. Proc. Second ARPA/NSF-ESPRIT Workshop on Invariance, Ponta Delgada, Azores (1993) 377–389Google Scholar
  19. [ås4]
    åström, K.: Object Recognition using Affine and Projective Invariants of Planar Sets. CODEN:LUFTD2/TFMA-3002/5002-SE, Lund, Sweden (1993)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1994

Authors and Affiliations

  • Kalle åström
    • 1
  1. 1.Dept of MathematicsLund Institute of TechnologyLundSweden

Personalised recommendations