Abstract

In this paper a novel approach to contour-based 2D shape recognition is proposed. The main idea is to characterize the contour of an object using the multifractional Brownian motion (mBm), a mathematical method able to capture the local self similarity and long-range dependence of a signal. The mBm estimation results in a sequence of Hurst coefficients, which we used to derive a fixed size feature vector. Preliminary experimental evaluations using simple classifiers with these feature vectors produce encouraging results, also in comparison with the state of the art.

Keywords

Feature Vector Hide Markov Model Fractional Brownian Motion Edit Distance Hurst Exponent 
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.

References

  1. 1.
    Campbell, R., Flynn, P.: A survey of free-form object representation and recognition techniques. Computer Vision and Image Understanding 81, 166–210 (2001)CrossRefMATHGoogle Scholar
  2. 2.
    Loncaric, S.: A survey of shape analysis techniques. Pattern Recognition 31(8), 983–1001 (1998)CrossRefGoogle Scholar
  3. 3.
    Suetens, P., Fua, P., Hanson, A.: Computational strategies for object recognition. ACM Compuiting Surveys 24(1), 5–61 (1992)CrossRefGoogle Scholar
  4. 4.
    Peltier, R., Véhel, J.L.: Multifractional brownian motion: definition and preliminary results. Technical Report Rapport de recherche no. 2645, INRIA (1995)Google Scholar
  5. 5.
    Véhel, J.L.: Fractal approaches in signal processing. Fractals 3, 755–775 (1995)MathSciNetCrossRefMATHGoogle Scholar
  6. 6.
    Ayache, A., Véhel, J.L.: The generalized multifractional brownian motion. Statistical Inference for Stochastic Processes 3, 7–18 (2000)MathSciNetCrossRefMATHGoogle Scholar
  7. 7.
    Mandelbrot, B., Ness, J.V.: Fractional brownian motions, fractional noises and applications. SIAM Review 10, 422–437 (1968)MathSciNetCrossRefMATHGoogle Scholar
  8. 8.
    Lundahl, T., Ohley, W., Kay, S., Siffert, R.: Fractional brownian motion: A maximum likelihood estimator and its application to image texture. IEEE Trans. on Medical Imaging 5, 152–161 (1986)CrossRefGoogle Scholar
  9. 9.
    SantAna, R., Coelho, R., Alcaim, A.: Text-independent speaker recognition based on the hurst parameter and the multidimensional fractional brownian motion model. IEEE Trans. on Audio, Speech and Language Processing 14(3) (2006)Google Scholar
  10. 10.
    Mandelboot, B.B., et al.: The Science of Fractal Images. Springer, New York (1988)Google Scholar
  11. 11.
    Chen, S., Keller, J., Crownover, R.: On the calculation of fractal features from images. IEEE Trans. om Pattern Analysis and Machine Intelligence 15 (1993)Google Scholar
  12. 12.
    Taylor, R., Lewis, P.: 2d shape signature based on fractal measurements. IEE Proc. of Vision, Image and Signal Processing 141(6), 422–430 (1994)CrossRefGoogle Scholar
  13. 13.
    Uemura, S., Haseyama, M., Kitajima, H.: Efficient contour shape description by using fractal interpolation functions. In: Proc. Int. Conf. Image Processing, vol. 1, pp. I–485–I–488 (2002)Google Scholar
  14. 14.
    Falconer, K.: Fractal Geometry: Mathematical Foundations and Applications. Wiley, Chichester (2003)CrossRefMATHGoogle Scholar
  15. 15.
    Bicego, M., Murino, V.: Investigating Hidden Markov Models’ capabilities in 2D shape classification. IEEE Trans. on Pattern Analysis and Machine Intelligence - PAMI 26(2), 281–286 (2004)CrossRefGoogle Scholar
  16. 16.
    Neuhaus, M., Bunke, H.: Edit distance-based kernel functions for structural pattern classification. Pattern Recognition 39, 1852–1863 (2006)CrossRefMATHGoogle Scholar
  17. 17.
    Coeurjolly, J.: Identification of the multifractional brownian motion. Bernoulli 11(6), 987–1008 (2005)MathSciNetCrossRefMATHGoogle Scholar
  18. 18.
    Brown, R.: A brief account of microscopical observations made in the months of June, July and August, 1827, on the particles contained in the pollen of plants; and on the general existence of active molecules in organic and inorganic bodies. Phil. Mag. 4(1828), 161–173Google Scholar
  19. 19.
    Samorodnitsky, G., Taqqu, M.: Stable non-Gaussian random processes. Chapman & Hall, Boca Raton (1994)MATHGoogle Scholar
  20. 20.
    Benassi, A., Jaffard, S., Roux, D.: Elliptic gaussian random processes. Matematica Iberoamericana 13(1), 19–89 (1997)MathSciNetCrossRefMATHGoogle Scholar
  21. 21.
    Bianchi, S.: Pathwise identification of the memory function of the multifractional brownian motion with application to finance. Int. J. of Theoretical and Applied Finance 8(2), 255–281 (2005)MathSciNetCrossRefMATHGoogle Scholar
  22. 22.
    Peltier, R., Véhel, J.L.: A new method for estimating the parameter of fractional brownian motion. Technical Report Rapport de recherche no. 2396, INRIA (1994)Google Scholar
  23. 23.
    Andreu, G., Crespo, A., Valiente, J.: Selecting the toroidal self-organizing feature maps (tsofm) best organized to object recognitio. In: Proc. of IEEE ICNN 1997, vol. 2, pp. 1341–1346 (1997)Google Scholar
  24. 24.
    Mollineda, R., Vidal, E., Casacuberta, F.: Cyclic sequence alignments: Approximate versus optimal techniques. Int. Journal of Pattern Recognition and Artificial Intelligence 16(3), 291–299 (2002)CrossRefGoogle Scholar
  25. 25.
    Peris, G., Marzal, A.: Fast cyclic edit distance computation with weighted edit costs in classification. In: Proc. of Int. Conf. on Pattern Recognition, vol. 4, pp. 184–187 (2002)Google Scholar
  26. 26.
    He, Y., Kundu, A.: 2-D shape classification using Hidden Markov Model. IEEE Trans. Pattern Analysis Machine Intelligence 13(11), 1172–1184 (1991)CrossRefGoogle Scholar
  27. 27.
    Arica, N., Yarman-Vural, F.: A shape descriptor based on circular Hidden Markov Model. In: IEEE Proc. Int. Conf. Pattern Recognition, vol. 1, pp. 924–927 (2000)Google Scholar
  28. 28.
    Bicego, M., Murino, V., Figueiredo, M.: Similarity-based classification of sequences using hidden markov models. Pattern Recognition 37(12), 2281–2291 (2004)CrossRefMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Manuele Bicego
    • 1
  • Alessandro Trudda
    • 1
  1. 1.DEIR - University of SassariSassariItaly

Personalised recommendations