Image restoration using fast modified reduced update Kalman filter

Wen-Rong Wu*, Amlan Kundu

*Corresponding author for this work

Research output: Contribution to conferencePaperpeer-review

Abstract

Some modifications to the reduced update Kalman filter (RUKF) as applied to the filtering of images corrupted by additive noise are proposed. The computational complexity of RUKF is reduced by reducing the state dimensionality. The RUKF is modified using the score-function-based approach to accommodate the non-Gaussian noise. The image is modeled as a nonstationary mean and stationary variance autoregressive Gaussian process. It is shown that the stationary variance assumption is reasonable if the nonstationary mean is computed by means of an edge and detail preserving spatial filter. Such a filter is described.

Original languageEnglish
Pages547-550
Number of pages4
DOIs
StatePublished - 9 Aug 1990
EventProceedings of the 1990 IEEE International Conference on Systems Engineering - Pittsburgh, PA, USA
Duration: 9 Aug 199011 Aug 1990

Conference

ConferenceProceedings of the 1990 IEEE International Conference on Systems Engineering
CityPittsburgh, PA, USA
Period9/08/9011/08/90

Fingerprint Dive into the research topics of 'Image restoration using fast modified reduced update Kalman filter'. Together they form a unique fingerprint.

Cite this