On Feature Extraction Capabilities of Fast Orthogonal Neural Networks

  • Bartłomiej Stasiak
  • Mykhaylo Yatsymirskyy
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4432)


The paper investigates capabilities of fast orthogonal neural networks in a feature extraction task for classification problems. Neural networks with an architecture based on the fast cosine transform, type II and IV are built and applied for extraction of features used as a classification base for a multilayer perceptron. The results of the tests show that adaptation of the neural network allows to obtain a better transform in the feature extraction sense as compared to the fast cosine transform. The neural implementation of both the feature extractor and the classifier enables integration and joint learning of both blocks.


Recognition Rate Multilayer Perceptron Linear Neural Network Error Recognition Rate Orthogonal Network 
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.
    Osowski, S.: Neural networks for information processing (in Polish). OWPW, Warsaw (2000)Google Scholar
  2. 2.
    Osowski, S., Nghia, D.D.: Fourier and wavelet descriptors for shape recognition using neural networks - a comparative study. Pattern Recognition 35, 1949–1957 (2002)zbMATHCrossRefGoogle Scholar
  3. 3.
    Stasiak, B., Yatsymirskyy, M.: Application of Fourier-Mellin Transform To Categorization of 3D Objects (in Polish). In: Proc. of the III Conference on Information Technologies, Gdańsk, Poland (2005)Google Scholar
  4. 4.
    Sikora, T., Makai, B.: Shape-adaptive DCT for generic coding of video. IEEE Trans. on Circuits Syst. Video Technol. 5, 59–62 (1995)CrossRefGoogle Scholar
  5. 5.
    Pan, Z., Rust, A., Bolouri, H.: Image Redundancy Reduction for Neural Network Classification using Discrete Cosine Transforms. In: Proc. of the International Joint Conference on Neural Networks, Como, Italy, vol. 3, pp. 149–154 (2000)Google Scholar
  6. 6.
    Jacymirski, M., Szczepaniak, P.S.: Neural realization of fast linear filters. In: Proc. of the 4th EURASIP - IEEE Region 8 International Symposium on Video/Image Processing and Multimedia Communications, pp. 153–157 (2002)Google Scholar
  7. 7.
    Stasiak, B., Yatsymirskyy, M.: Fast orthogonal neural networks. In: Rutkowski, L., Tadeusiewicz, R., Zadeh, L.A., Żurada, J.M. (eds.) ICAISC 2006. LNCS (LNAI), vol. 4029, pp. 142–149. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  8. 8.
    Rao, K.R., Yip, P.: Discrete cosine transform. Academic Press, San Diego (1990)zbMATHGoogle Scholar
  9. 9.
    Jacymirski, M.: Fast homogeneous algorithms of cosine transforms, type II and III with tangent multipliers (in Polish). In: Automatics, vol. 7, pp. 727–741. AGH University of Science and Technology Press, Cracow (2003)Google Scholar
  10. 10.
    Stasiak, B., Yatsymirskyy, M.: Recursive learning of fast orthogonal neural networks. In: Proc. of the International Conf. on Signals and Electronic Systems, pp. 653–656 (2006)Google Scholar
  11. 11.
    Rutkowski, L.: Methods and techniques of artificial intelligence (in Polish). Polish Scientific Publishers PWN, Warszawa (2005)Google Scholar
  12. 12.
    Hettich, S., Bay, S.D.: The UCI KDD Archive. University of California, Department of Information and Computer Science, Irvine, CA (1999),

Copyright information

© Springer Berlin Heidelberg 2007

Authors and Affiliations

  • Bartłomiej Stasiak
    • 1
  • Mykhaylo Yatsymirskyy
    • 1
  1. 1.Institute of Computer Science, Technical University of Łódź, ul. Wólczańska 215, 93-005 ŁódźPoland

Personalised recommendations