Estimation of the optimal regularization parameter of an iterative wavelet algorithm for signal recovery

  • Yu. E. Voskoboynikov
Analysis and Synthesis of Signals and Images


Two methods of statistical estimation of the optimal regularization parameter of a nonlinear algorithm for signal recovery are proposed, one of which is based on the optimality criterion and the other one on the residual principle. These methods have simple algorithmic implementation and do not need a priori information about the quantitative characteristics of the sought solution. The results of numerical experiments show the effectiveness of the method based on the optimality criterion.


signal and image recovery nonlinear regularization algorithms threshold wavelet filtering estimation of optimal regularization parameter 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    A. N. Tikhonov and V. Ya. Arsenin, Methods for Solving Incorrect Problems (Nauka, Moscow, 1986) [in Russian].Google Scholar
  2. 2.
    A. N. Tikhonov, A. V. Goncharskii, V. V. Stepanov, et al., Regularization Algorithms and a Priori Information (Nauka, Moscow, 1988) [in Russian].Google Scholar
  3. 3.
    V. V. Voevodin and Yu. A. Kuznetsov, Matrices and Computations (Nauka, Moscow, 1984) [in Russian].zbMATHGoogle Scholar
  4. 4.
    V. A. Morozov and A. I. Grebennikov, Methods for Solving Incorrect Problems: Algorithmic Aspect (Moscow State University Press, Moscow, 1992) [in Russian].Google Scholar
  5. 5.
    Yu. E. Voskoboinikov, N. G. Preobrazhensky, and A. I. Sedel’nikov, Mathematical Treatment of the Experiment in Molecular Gas Dynamics (Nauka, Novosibirsk, 1984) [in Russian].Google Scholar
  6. 6.
    Yu. E. Voskoboinikov, Stable Algorithms for Solving Inverse Problems of Measurement (Novosibirsk State University of Architecture and Civil Engineering, Novosibirsk, 2007) [in Russian].Google Scholar
  7. 7.
    I. Daubechies, M. Defrise, and C. De Mol, “An Iterative Thresholding Algorithm for Linear Inverse Problems with a Sparsity Constraint,” Commun. Pure and Appl. Math. 57(11), 1413–1457 (2004).zbMATHCrossRefGoogle Scholar
  8. 8.
    M. A. Figueiredo and R. D. Nowak, “An EM Algorithm for Wavelet-Based Image Restoration,” IEEE Trans. Image Process. 12(8), 906–916 (2003).MathSciNetADSCrossRefGoogle Scholar
  9. 9.
    C. Vonesch and M. Unser, “A Fast Thresholded Landweber Algorithm for Wavelet-Regularized Multidimensional Deconvolution,” IEEE Trans. Image Process. 17(4), 539–549 (2008).MathSciNetADSCrossRefGoogle Scholar
  10. 10.
    C. K. Chui, An Introduction to Wavelets (Mir, Moscow, 2002; Academic Press, 1992).Google Scholar
  11. 11.
    S. Mallat, “A Theory of Multiresolution Signal Expansion: the Wavelet Representation,” IEEE Trans. Pattern Anal. Machine Intell. 11(9), 674–693 (1989).ADSzbMATHCrossRefGoogle Scholar
  12. 12.
    S. Mallat, “Multiresolution Approximation and Wavelet Orthonormal Bases of L 2(R),” Trans. AMS. 315(1), 69–87 (1989).MathSciNetzbMATHGoogle Scholar
  13. 13.
    Yu. E. Voskoboinikov, A. V. Gochakov, and A. B. Kolker, Signal and Image Filtering: Fourier and Wavelet Algorithms (with examples in Mathcad) (Novosibirsk State University of Architecture and Civil Engineering, Novosibirsk, 2010), Scholar
  14. 14.
    Yu. E. Voskoboinikov and A. V. Gochakov, “Estimation of Optimal Threshold Values in Algorithms of Wavelet Filtration of Images,” Avtometriya 47(2), 3–14 (2011) [Optoelectron., Instrum. Data Process. 47 (2), 105–113 (2011)].Google Scholar
  15. 15.
    Yu. E. Voskoboinikov, “Estimation of the Optimal Parameter of Regularization Algorithms of Image Reconstruction,” Avtometriya, No. 3, 68–77 (2011).Google Scholar
  16. 16.
    Yu. E. Voskoboinikov, Stable Methods and Algorithms for Parametric Identification (Novosibirsk State University of Architecture and Civil Engineering, Novosibirsk, 2006) [in Russian].Google Scholar

Copyright information

© Allerton Press, Inc. 2013

Authors and Affiliations

  1. 1.Novosibirsk State University of Architecture and Civil EngineeringNovosibirskRussia

Personalised recommendations