Local Approximation Signal and Image Processing

1D Adaptive-Scale DemoBox

for MATLAB version 6.5 or later


The 1D Adaptive-Scale Selection DemoBox is a set of MATLAB routines for 1D signal denoising. They implement a recent new development in the area of statistical scale-adaptive local approximation techniques.

The main algorithms are prepared as demos, so that they can be executed in a straightforward manner. These demos reproduce figures and results from the publications by the authors of the LASIP project and their collaborators.

All the provided demos are open-source, and may be modified and tuned to be exploited with other data. This DemoBox is available free-of-charge for educational and non-profit scientific research, enabling others researchers to understand and reproduce our work. Any unauthorized use of the LASIP routines for industrial or profit-oriented activities is expressively prohibited.



The main routines provided in this DemoBox are the following:

demo_CreateLPAKernels.m

LPA kernel design
Calculates the LPA convolution smoothing and differentiation kernels of polynomial approximation and its frequency response characteristic, and draws them.
demo_LPAICI_1D.m

LPA-ICI denoising
Performs the Anisotropic LPA-ICI denoising on observations which are contaminated by additive white Gaussian noise.
demo_MedianICI_1D.m

Median-ICI denoising
Performs the Anisotropic Median-ICI denoising on observations which are contaminated by the additive white Gaussian and impulsive noise.
demo_IdealInvariantScale1D.m

Oracle Invariant scale selection
Illustrates the problem of invariant scale selection. The invariant ideal scale h of the LPA estimator is found for the noisy signal assuming that the true signal is known.
demo_IdealVaryinigScale1D.m

Oracle Varying scale selection
Illustrates optimal scale selection for every point of the signal. The varying ideal scale h of the LPA estimator is found for the noisy signal assuming that the true signal is known. Ideal scale is selected by minimization of mean square error in a point-wise manner.
Any unauthorized use of the LASIP routines for industrial or profit-oriented activities is expressively prohibited. By downloading any of the LASIP files, you implicitly agree to all the terms of the LASIP limited license PDF.


CLICK HERE TO DOWNLOAD .ZIP PACKAGE


Tampere University of Technology - Department of Signal Processing - Transforms and Spectral Methods Group