Improved Block Kalman Filter for Degraded Image Restoration
Cui Liu, Ying Zhang, Haoqian Wang, Xingzheng Wang · 2013
This paper is mainly concerned with the problem of how to set the initial conditions of two-dimensional(2-D) block Kalman filter on degraded image for image restoration. The proposed approach incorporates layering and interpolation process into the degraded image that has been corrupted by blur and additive noise. The innovation of this paper are setting reasonable filtering initial conditions which are associated with image information and increase interpolation operation with edge protection function. Compared with the reported paper, the presented method gives a sharper restored image, especially, which has little ringing distortions near the boundaries.