Title :
Least squares optimization of a polynomial threshold for wavelet domain denoising
Author :
Smith, Christopher B. ; Akopian, David ; Agaian, Sos S.
Author_Institution :
Dept. of Electr. Eng., Texas Univ., San Antonio, TX, USA
fDate :
31 Aug.-4 Sept. 2004
Abstract :
Wavelet based techniques have been used for a number of years to denoise signals. This paper focuses on optimizing a polynomial based non-linear threshold. This threshold has several features that make it well suited for use in optimized and adaptive frameworks. The optimization of this threshold is presented using a least squares based technique and the results are compared to two traditional wavelet threshold techniques.
Keywords :
adaptive signal processing; least squares approximations; optimisation; polynomials; signal denoising; wavelet transforms; least squares based technique; least squares optimization; optimization; polynomial based nonlinear threshold; signal denoising; wavelet domain denoising; Additive white noise; Discrete wavelet transforms; Equations; Filtering; Least squares methods; Noise reduction; Polynomials; Smoothing methods; Wavelet domain; Wideband;
Conference_Titel :
Signal Processing, 2004. Proceedings. ICSP '04. 2004 7th International Conference on
Print_ISBN :
0-7803-8406-7
DOI :
10.1109/ICOSP.2004.1452593
