Abstract
Fourier amplitude spectrum is often applied in pattern recognition problems due to its shift invariance property. The phase information, which is frequently rejected, may however be also important from the classification point of view. In this paper, fast orthogonal neural network (FONN) is used to compute amplitude spectrum in an adaptable way, enabling to extract more class-relevant information from input data. The complete architecture of the neural classifier system is presented. The proposed solution is compared to standard multilayer perceptron on an artificially generated dataset, proving its superiority in terms of computational complexity and generalization properties.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Derrode, S., Ghorbel, F.: Robust and efficient Fourier and Mellin transform approximations for gray-level image reconstruction and complete invariant description. Computer Vision and Image Understanding 83, 57–78 (2001)
Jacymirski, M.: Fast homogeneous algorithms of cosine transforms, type II and III with tangent multipliers. Automatics 7, 727–741 (2003) (in Polish)
Jacymirski, M., Szczepaniak, P.S.: Neural realization of fast linear filters. In: Proceedings of the 4th EURASIP - IEEE Region 8 International Symposium on Video/Image Processing and Multimedia Communications, pp. 153–157 (2002)
Milanese, R., Cherbuliez, M.: A rotation-, translation-, and scale-invariant approach to content-based image retrieval. Journal of Vision Communication and Image Representation 10, 186–196 (1999)
Oppenheim, A.V., Hayes, M.H., Lim, J.S.: Iterative procedures for signal reconstruction from Fourier transform phase. Optical Engineering 21, 122–127 (1982)
Osowski, S.: Neural networks for information processing. Oficyna Wydawnicza Politechniki Warszawskiej, Warsaw (2000) (in Polish)
Rao, K.R., Yip, P.: Discrete cosine transform. Academic Press, San Diego (1990)
Rutkowski, L.: Methods and Techniques of Artificial Intelligence. Państwowe Wydawnictwa Naukowe, Warsaw (2005) (in Polish)
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)
Szczepaniak, P.S.: Intelligent computations, fast transforms and classifiers. EXIT Academic Publishing House, Warsaw (2004) (in Polish)
Tadeusiewicz, R., Gąciarz, T., Borowik, B., Leper, B.: Discovering neural network proprieties by means of C# programs. Polska Akademia Umiejętności, Cracow (2007) (in Polish)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Stasiak, B., Yatsymirskyy, M. (2009). Fast Orthogonal Neural Network for Adaptive Fourier Amplitude Spectrum Computation in Classification Problems. In: Cyran, K.A., Kozielski, S., Peters, J.F., Stańczyk, U., Wakulicz-Deja, A. (eds) Man-Machine Interactions. Advances in Intelligent and Soft Computing, vol 59. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-00563-3_34
Download citation
DOI: https://doi.org/10.1007/978-3-642-00563-3_34
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-00562-6
Online ISBN: 978-3-642-00563-3
eBook Packages: EngineeringEngineering (R0)