Recursive Wiener filtering for image restoration

The Wiener filter technique is known to be one of the most powerful methods for image restoration. The algorithm however is non-recursive and in its original form, is computationally extremely involved as it requires inversion of large matrix. In order to make it computationally feasible Fourier Transformations are used. In this paper, a backward recursive solution of Wiener filtering technique is presented. The algorithm exploits the band structure of the correlation matrices.