Geometric Invariant Curve and Surface Normalization

  • Sait Sener
  • Mustafa Unel
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4142)


In this work, a geometric invariant curve and surface normalization method is presented. Translation, scale and shear are normalized by Principal Component Analysis (PCA) whitening. Independent Component Analysis (ICA) and the third order moments are then employed for rotation and reflection normalization. By applying this normalization, curves and surfaces that are related by geometric transformations (affine or rigid) can be transformed into a canonical representation. Proposed technique is verified with several 2D and 3D object matching and recognition experiments.


Machine Intelligence Hausdorff Distance Independent Component Analysis Order Moment Iterative Close Point 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Lin, C.S., Hwang, C.L.: New Forms of Shape Invariants From Elliptic Fourier Descriptors. Pattern Recognition 20(5), 535–545 (1987)CrossRefGoogle Scholar
  2. 2.
    Persoon, E., Fu, K.S.: Shape Discrimination Using Fourier Descriptors. IEEE Transactions on Pattern Analysis and Machine Intelligence 8(3), 388–397 (1986)CrossRefGoogle Scholar
  3. 3.
    Taubin, G., Cuikerman, F., Sullivan, S., Ponce, J., Kriegman, D.J.: Parameterized families of polynomials for bounded algebraic curve and surface fitting. IEEE Transactions on Pattern Analysis and Machine Intelligence 16(3), 287–303 (1994)MATHCrossRefGoogle Scholar
  4. 4.
    Cohen, F.S., Huang, Z.H., Yang, Z.: Invariant matching and identification of curves using B-spline curve representation. IEEE Transactions on Image Processing 4, 1–10 (1995)CrossRefGoogle Scholar
  5. 5.
    Huang, Z.H., Cohen, F.S.: Affine invariant B-spline moments for curve matching. Image Processing 5(10), 1473–1480 (1996)CrossRefGoogle Scholar
  6. 6.
    Rui, Y., She, A., Huang, T.S.: A modified Fourier descriptor for shape matching in MARS. In: Chang, S.K. (ed.) Image Databases and Multimedia Search. Series of software engineering and knowledge engineering, vol. 8, pp. 165–180. World Scientific, SingaporeGoogle Scholar
  7. 7.
    Werman, M., Weinshall, D.: Similarity and affine Invariant Distances Between 2D Point Sets. IEEE Transactions on Pattern Analysis and Machine Intelligence 17(8), 810–814 (1995)CrossRefGoogle Scholar
  8. 8.
    Wolovich, W.A., Unel, M.: The Determination of Implicit Polynomial Canonical Curves. IEEE Transactions on Pattern Analysis and Machine Intelligence 20(10), 1080–1090 (1998)CrossRefGoogle Scholar
  9. 9.
    Faugeras, O.R., Hebert, M.: The Representation, Recognition, and Locating of 3-D Objects. The International Journal of Robotics Research 5(3) (1986)Google Scholar
  10. 10.
    Arbter, K.: Affine-Invariant Fourier Descriptors. In: From Pixels to Features. Elseiver Science, Amsterdam, The Netherlands (1989)Google Scholar
  11. 11.
    Shen, D., Ip, H.: Generalized Affine Invariant Image Normalization. IEEE Transactions on Pattern Analysis and Machine Intelligence 19(5), 431–440 (1997)CrossRefGoogle Scholar
  12. 12.
    Avritris, Y., Xirouhakis, Y., Kollias, S.: Affine-Invariant Curve Normalization for Object Shape Representation, Classification and Retrieval. Machine Vision and Applications 13(2), 80–94 (2001)CrossRefGoogle Scholar
  13. 13.
    Faber, T., Stokely, E.: Orientation of 3-D structures in medical images. IEEE Trans. on Pattern Analysis and Machine Intelligence 10(5), 626–634 (1988)CrossRefGoogle Scholar
  14. 14.
    Cyganski, D., Orr, J.: Applications of tensor theory to object recognition and orientation determination. IEEE Trans. on Pattern Analysis and Machine Intelligence 7(6), 662–674 (1985)CrossRefGoogle Scholar
  15. 15.
    Haralick, R., Joo, H., Lee, C., Zhuang, X., Vaidya, V., Kim, M.: Pose estimation from corresponding point data. IEEE Trans. on Pattern Analysis and Machine Intelligence 19, 1426–1446 (1989)Google Scholar
  16. 16.
    Besl, P., McKay, N.: A method for registration of 3D shapes. IEEE Trans. on Pattern Analysis and Machine Intelligence 14(2), 239–256 (1992)CrossRefGoogle Scholar
  17. 17.
    Zhang, Z.: Iterative Point Matching for Registration of Free-Form Curves and Surfaces. International J. Computer Vision 13(2), 119–152 (1994)CrossRefGoogle Scholar
  18. 18.
    Ferrie, F.P., Levine, M.D.: Integrating Information from Multiple Views. In: Proc. IEEE Workshop on Computer Vision, Miami Beach, Fla., pp. 117–122 (1987)Google Scholar
  19. 19.
    Potmesil, M.: Generating Models for Solid Objects by Matching 3D Surface Segments. In: Proc. Int. Joint Conf. Artificial Intelligence, Karlsruhe, Germany, pp. 1,089–1,093 (1983)Google Scholar
  20. 20.
    Blais, G., Levine, M.D.: Registering Multiview Range Data to Create 3D Computer Objects. IEEE Trans. on Pattern Analysis and Machine Intelligence 17(8), 820–824 (1995)CrossRefGoogle Scholar
  21. 21.
    Papaioannou, G., Karabassi, E., Theoharis, T.: Reconstruction of Three-Dimensional Objects through Matching of Their Parts. IEEE Trans. on Pattern Analysis and Machine Intelligence 24(1), 114–124 (2002)CrossRefGoogle Scholar
  22. 22.
    Fukunaga, K.: Introduction to Statistical Pattern Recognition, 2nd edn. Academic Press, New York (1990)MATHGoogle Scholar
  23. 23.
    Lee, T.W.: Independent Component Analysis- Theory and Applications. Kluwer Academic Publishers, Dordrecht (1998)MATHGoogle Scholar
  24. 24.
    Hyvrinen, A.: Fast and robust fixed-point algorithms for independent component analysis. IEEE Trans. On Neural Networks 10(3), 626–634 (1999)CrossRefGoogle Scholar
  25. 25.
    Ballard, D.H.: Generalizing the Hough transform to detect arbitrary shapes. Putt. Recogn. 13(2), 111–122 (1981)MATHCrossRefGoogle Scholar
  26. 26.
    Yi, X., Camps, O.C.: Robust occluding contour detection using the Hausdorff distance. In: Proc. of IEEE Conf. on Vision and Pattern Recognition, CVPR 1997, San Juan, PR, pp. 962–967 (1997)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Sait Sener
    • 1
  • Mustafa Unel
    • 2
  1. 1.Institute of InformaticsIstanbul Technical UniversityTurkey
  2. 2.Faculty of Engineering and Natural SciencesSabanci UniversityTurkey

Personalised recommendations