Restoration of Motion-Blurred Image by RLS Wiener Smoother and Filter

Hitherto, a variety of image restoration techniques have been applied to the image restoration problems degraded by the blur and the observation noise. This paper examines, for the first time, to restore the degraded image by the RLS Wiener fixed-point smoother and filter. In this paper, it is assumed that the degraded image is generated in terms of blur and additional white observation noise. In the RLS Wiener estimators, the following information is used: (1) the system matrix for the state vector, (2) the variance of the state vector, (3) the variance of the white observation noise, and (4) the observation vector. As is shown in the simulation example, the observation vector is related to the point-spread function (PSF), which is known as a parameter to cause blur in two-dimensional images. A numerical simulation example shows that the proposed image restoration technique, for the degraded image including the blur, by the RLS Wiener fixed-point smoother and filter is feasible