Adaptive filtering approaches for colour image and video restoration

Abstract

An adaptive simplified model Kalman filter (ASMKF) is developed for image and video impulsive noise suppression. The ASMKF is more effective than the median filter (MF) and the robust reduced update Kalman filter (RRUKF) in suppressing the impulsive noise, especially when the signal-to-noise ratio is low. Further, a hybrid filter is presented for colour image and video restoration in a mixed noise environment, where both the impulsive and correlated noise may be present. The proposed hybrid filter is composed of two stages, where the first stage removes the impulsive noise while the second removes the correlated noise. The ASMKF is suggested for the first stage of the hybrid filter. In the second stage of the proposed hybrid filter, a discrete wavelet transform (DWT) filter formulated using a biorthogonal wavelet with adaptive shrinkage is applied on the impulsive-noise-free image obtained from the first stage. The efficacy of the developed ASMKF and the proposed hybrid filter are illustrated through implementation results on colour image and video restoration.