XFF: A simple method to extract fractal features for 2D object recognition

  • Matteo Baldoni
  • Cristina Baroglio
  • Davide Cavagnino
Poster Papers
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1451)


Automatic recognition of objects from their visual representation is a hard and computationally expensive task, mainly because it is difficult to extract the necessary discriminant information from the raw data. The current approaches to image classification commonly exploit some geometrical models of the objects of interest. The classification process is based on the comparison between the image at hand and the models for the classes: the object's class will be the one of the closest model. In this paper we present XFF, a new method for representing 2-D images, based on the extraction of a set of fractal features which exploits the approximation of an image with an Iterated Function System, a technique that is already at the basis of many successful image compression tools. One of the advantages of these features is that they can be used directly to train an adaptive classifier, without the need of any a priori knowledge.


Recognition Rate Hide Neuron Image Classification Fractal Feature Iterate Function System 
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.


  1. 1.
    M. Baldoni, C. Baroglio, D. Cavagnino, and G. Lo Bello. Extraction of Discriminant Features from Image Fractal Encoding. In M. Lenzerini, editor, Proc. of AI*IA 97: Advances in Artificial Intelligence, volume 1321 of LNAI, pages 127–138. Springer-Verlag, 1997.Google Scholar
  2. 2.
    M. Barnsley. Fractals Everywhere. Academic Press, San Diego, 1988.Google Scholar
  3. 3.
    M. Barnsley and S. Demko. Iterated function systems and the global construction of fractals. In The Proc. of the Royal Society of London, vol. A399, 243–275, 1985.Google Scholar
  4. 4.
    M. Barnsley and L. P. Hurd. Fractal Image Compression. AK Peters, Ltd., Wellesley, Massachusetts, 1993.Google Scholar
  5. 5.
    P. Besl and R. Jain. Three dimensional object recognition. ACM Computing Surveys, (17):75–154, 1985.Google Scholar
  6. 6.
    R. Chin and C. Dyer. Model-based recognition in robot vision. ACM Computing Surveys, (18):67–108, 1986.Google Scholar
  7. 7.
    A. M. Erkmen and H. E. Stephanou. Information Fractals for Evidential Pattern Classification. IEEE Trans. on Sys., Man, and Cyb., 20(5):1103–1114, 1990.Google Scholar
  8. 8.
    K. Falconer. Fractal Geometry, Mathematical Foundations and Applications. John Wiley & Sons Ltd., Chichester, UK, 1990.Google Scholar
  9. 9.
    Y. Fisher. Fractal Compression: Theory and Application to Digital Images. Springer Verlag, New York, 1994.Google Scholar
  10. 10.
    B. Freisleben, J. H. Greve, and J. Löber. Recognition of Fractal Images using a Neural Network. In New Trends in Neural Computation, IWANN '93, volume 686 of LNCS, pages 632–637. Springer-Verlag, 1993.Google Scholar
  11. 11.
    R. C. Gonzales and R. E. Woods. Digital Image Processing. Addison-Wesley Publishing Company, 1992.Google Scholar
  12. 12.
    A. Imiya, Y. Fujiwara, and T. Kawashima. A Metric of Planar Self-Similar Forms. In P. Perner, P. Wang, and A. Rosenfeld, editors, Advances in Structural and Syntactical Pattern Recognition, SSPR'96, vol. 1121 of LNCS, pages 100–109. Springer-Verlag, 1996.Google Scholar
  13. 13.
    A. De Marchi and Cassi. Modelli matematici di colonizzazione lichenica ottenuti mediante l'esame di equazioni frattali. Notiziario della Society Lichenologica Italiana, 5, 1992.Google Scholar
  14. 14.
    D. Michie, D. J. Spiegelhalter, and C. C. Taylor. Machine Learning, Neural and Statistical Classification. Ellis Horwood Series in AI. Prentice Hall, 1994.Google Scholar
  15. 15.
    M. F. Moller. A scaled conjungate gradient algorithm for fast supervised learning. Neural Networks, 6:525:533, 1993.CrossRefGoogle Scholar
  16. 16.
    D. R. Morse, J. H. Lawton, M. M. Dodson, and M. H. Williamson. Fractal dimension of vegetation and the distribution of anthropod body lengths. Nature, 314:731–733, 1985.CrossRefGoogle Scholar
  17. 17.
    L. O'Gorman. Basic techniques and symbol-level recognition — an overview. In K. Tombre R. Kasturi, editor, Graphics Recognition, Methods and Applications, volume 1072 of LNCS, pages 1–12. Springer-Verlag, 1995.Google Scholar
  18. 18.
    A. P. Pentland. Fractal-Based Description of Natural Scenes. IEEE Trans. Pattern Analysis and Machine Intelligence, (PAMI-6):661–674, 1984.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1998

Authors and Affiliations

  • Matteo Baldoni
    • 1
  • Cristina Baroglio
    • 1
  • Davide Cavagnino
    • 1
  1. 1.Dipartimento di InformaticaUniversità degli Studi di TorinoTorinoItaly

Personalised recommendations