In this paper we present a 3D adaptive nonlinear filter, namely the 3D adaptive CPWLN, based on the Canonical Piece Wise-Linear Network with an LMS L-filter type of adaptation. This filter is used to equalize nonlinear channel effect and remove impulsive/or mixed impulsive and Additive White Gaussian noise from video sequences. First, motion compensation is performed by a robust estimator. Then, a 3-D CPWLN LMS L-filter is applied. The overall combination is able to adequately remove undesired effects of communication channel and noise. Computer simulations on real-world image sequences are included. The algorithm yields promising results in terms of both objective and subjective quality of the restored sequence.

An important area in visual communications is the restoration of image sequences degraded by channel and noise. Since a nonlinearity is commonly involved in image transmitting procedure, an adaptive nonlinear equalizer is required. In this paper we address this problem by proposing a 3D adaptive nonlinear filter, namely the 3D adaptive Volterra filter with an LMS type of adaptation algorithm. This adaptive filter is used for equalizing an unknown 2-D channel with some point-wise nonlinearity and restoring image sequences degraded by this channel. Prior to filtering, motion is estimated from the sequence and compensated for. For this purpose, a robust region-recursive Higher Order Statistics (HOS) based motion estimation method is employed. The overall combination is able to adequately remove undesired effects of communication channel and noise. The performance of this algorithm is examined using real image sequences demonstrated by experimental results.