𝔖 Bobbio Scriptorium
✦   LIBER   ✦

Robust Wiener filters

✍ Scribed by Saleem A. Kassam; Tong Leong Lim

Publisher
Elsevier Science
Year
1977
Tongue
English
Weight
723 KB
Volume
304
Category
Article
ISSN
0016-0032

No coin nor oath required. For personal study only.

✦ Synopsis

The performance of minimum mean-square-error estimafion filters for signals in additive noise can deteriorate considerably for deviations of the actual signal and noise power spectral densities (PSD's) from assumed, nominal densities. We consider two classes of PSD's which are useful models for the signal and noise when their PSD's are not precisely known. For these classes, robust fillers which are saddlepoints for mean-squareerror performance are derived. The robust filters achieve their worst performance for pairs of least-favorable signal and noise PSD's for which they are the optimum filters. It is shown by a numerical example that the robust filter can be very useful in maintaining a reasonable error performance over the whole of the classes of PSD's.

πŸ“œ SIMILAR VOLUMES

Optimum non-linear Wiener filters
Optimum non-linear Wiener filters
✍ M. Rudko; D.D. Weiner πŸ“‚ Article πŸ“… 1979 πŸ› Elsevier Science 🌐 English βš– 613 KB

## General conditions are given for the optima&y of non-linear Wiener filters which minimize the mean-square difference between the desired and actual filter outputs. These conditions, which are a generalization of the Wiener-Hopf equation are applied to the Gaussian case and the kernels of the opt

Image restoration by using multiple Wien
Image restoration by using multiple Wiener filters
✍ Ryohei Nishimiya; Akira Taguchi πŸ“‚ Article πŸ“… 2002 πŸ› John Wiley and Sons 🌐 English βš– 934 KB

## Abstract We propose a method that uses multiple Wiener filters based on region decomposition to restore natural images degraded by Gaussian noise. Usually, a Wiener filter is designed to be optimal for the entire image. However, because natural images are highly nonstationary, an effective metho