International Conference on System, Man and Cybernetics,
vol. 2, pp. 1671-1675, Oct. 1995
An Adaptive Filtering
Interpolator Using Neural Networks
Department of Communication & Electronic
Engineering, South China Univ. of Technology, Guangzhou, China
PDF File (416K)
interpolators presented by Lucke and Stocker (1993) have advantages in reducing
interpolation error in image background clutter-suppression systems especially
for data with low sampling rates. Before they are to be applied, a fixed
parameter alpha should be predetermined. The authors think if the parameter
alpha is well adjusted, it may also be useful to recover an image from a less
densely sampled image. Experiments show that interpolation error relies greatly
on the parameter alpha and the best values of alpha for certain images are much
different. Therefore, how to determine the values of alpha becomes the key
problem for this application. In this paper, the authors develop a neural
network based adaptive system to automatically adjust the value of alpha . A
modified robust BP algorithm is used in the training procedure for the authors'
special use. Simulation results show that alpha can be generated automatically
by the neural networks instead of being blindly predetermined to a fixed value.
Compared to the interpolator with best fixed parameter alpha , interpolation
results are also improved.