This paper proposes a novel realization of nonlinear filters suitable
for the edge-preserving smoothing of an image degraded by a mixed nois
e environment composed of the the Gaussian and impulsive noises. This
filter consists of a layered neural network and a median filter. By us
ing layered neural networks, the parameters of the proposed filter can
adapt itself to the various noisy environments through the learning o
f a training image. The training method of the parameter of response f
unctions is also proposed. These parameters have important effects for
the performance of the proposed filters. An example is shown to illus
trate the utility of the proposed filter. (C) 1998 The Franklin Instit
ute. Published by Elsevier Science Ltd.