Work is described in which neural network techniques have been used to
compress single and moving images. For the still images, two differen
t types of neural network have been examined: the multi-layer perceptr
on and the Kohonen self-organizing network. In many of the application
s in which there is a need for image compression, moving images are in
volved. It is shown how the Kohonen network can be used to compress mo
ving images by utilizing the redundancy between consecutive frames. Al
so addressed is how neural networks may be made adaptive, taking into
account changes in the scenes they are required to compress.