Title :
An iterative method for designing separable Wiener filters
Author :
Yoo, Chang D. ; Bace, Matthew M. ; Lim, Jae S.
Author_Institution :
Res. Lab. of Electron., MIT, Cambridge, MA, USA
fDate :
1/1/1995 12:00:00 AM
Abstract :
Presents a technique for designing the optimal (in the mean square error sense) separable 2D filter for recovering a signal from a noise-corrupted signal when the joint statistics of the signal and noise are known. A set of nonlinear equations in the design parameters is derived, and an iterative algorithm to solve them is presented. The algorithm is shown to be nondivergent in theory and rapidly convergent in practice. The results of applying the separable filter design algorithm to several typical image recovery problems are given. In most cases, the performance of the resulting separable filter is similar to that of the optimal nonseparable filter with the same region of support
Keywords :
FIR filters; Wiener filters; convergence of numerical methods; image reconstruction; iterative methods; least mean squares methods; nonlinear equations; signal reconstruction; two-dimensional digital filters; 2D filter; convergence; design algorithm; image recovery problems; iterative method; joint statistics; mean square error; noise-corrupted signal; nonlinear equations; performance; separable Wiener filters; Algorithm design and analysis; Design methodology; Error analysis; Image converters; Iterative algorithms; Iterative methods; Mean square error methods; Nonlinear equations; Signal design; Wiener filter;
Journal_Title :
Signal Processing, IEEE Transactions on
