Adaptive synthesis of a wavelet transform using fast neural network

• Autorzy: Stolarek J.
• Języki publikacji: EN

Abstrakty

EN

This paper introduces a new method for an adaptive synthesis of a wavelet transform using a fast neural network with a topology based on the lattice structure. The lattice structure and the orthogonal lattice structure are presented and their properties are discussed. A novel method for unsupervised training of the neural network is introduced. The proposed approach is tested by synthesizing new wavelets with an expected energy distribution between low- and high-pass filters. Energy compaction of the proposed method and Daubechies wavelets is compared. Tests are performed using sound and image signals.

Słowa kluczowe

EN

wavelets; neural networks; filter parametrization; fast algorithms

• Wydawca: Polska Akademia Nauk, Wydział IV Nauk Technicznych
• Czasopismo: Bulletin of the Polish Academy of Sciences. Technical Sciences
• Rocznik: 2011
• Tom: Vol. 59, nr 1
• Strony: 9--13
• Opis fizyczny: Bibliogr. 10 poz., rys., tab.

Twórcy

autor

Stolarek J.

• Institute of Information Technology, Technical University of Lodz, 215 Wólczańska St., 90-924 Łódź, Poland,

Bibliografia

• [1] P. Lipiński and M. Yatsymirskyy, “On synthesis of 4-tap and 6-tap reversible wavelet filters”, Electrotechnical Review 12, 284–286 (2008).
• [2] P. Rieder, J. Gotze, J.S. Nossek, and C.S. Burrus, “Parameterization of orthogonal wavelet transforms and their implementation”, Circuits and Systems II: Analog and Digital Signal Processing, IEEE Trans. 45 (2), 217–226 (1998).
• [3] P.P. Vaidyanathan and P.-Q. Hoang, “Lattice structures for optimal design and robust implementation of two-channel perfectreconstruction QMF banks”, Acoustics, Speech and Signal Processing, IEEE Trans. 36 (1), 81–94 (1988).
• [4] M. Yatsymirskyy, “Lattice structures for synthesis and implementation of wavelet transforms”, J. Applied Computer Science 17 (1), 133–141 (2009).
• [5] J.S. Walker, A Primer on Wavelets and Their Scientific Applications, Chapman & Hall, London, 2008.
• [6] B. Stasiak and M. Yatsymirskyy, “Fast orthogonal neural networks”, Lecture Notes in Computer Science 4029, 142–149 (2006).
• [7] S. Osowski, Neural Networks to Information Processing, Warsaw University of Technology Publishing House, Warszawa, 2006.
• [8] J. Stolarek, “Realization of Daubechies transform using lattice structure”, The Collection of Scientific Works of ISDMCI 2, 188–192 (2009).
• [9] J. Stolarek and M. Yatsymirskyy, “Fast neural network for synthesis and implementation of orthogonal wavelet transform”, Image Processing & Communications Challenges 1, 87–97 (2009).
• [10] S. Osowski, “Signal flow graphs and neural networks”, Biological Cybernetics 70 (4), 387–395 (1994).