Template synthesis of cellular neural networks for information coding and decoding

The use of analog cellular neural networks (CNNs) for information coding and decoding, especially for the case of moving images, is described. The dynamics of the coding (C-) and decoding (D-) CNNs are described by generalized CNN state equations. The C-CNN encodes the image by structural compression and halftoning. The D-CNN decodes the received data through a reconstruction process so as to almost recognize the original input to the C-CNN. The importance of the compression and quantization technique lies in the ability to make the computations with only local connections. A dynamic quantization is performed in the C-CNN to decide the binary value of each pixel from the neighboring values. In order to reduce the error between the original gray image and the reconstructed halftone image, the template synthesis problem is addressed from the viewpoint of energy minimization. The structural compression template synthesis problem is discussed from the viewpoints of topological and regularization theories. The structurally compressed image is regenerated in the D-CNN by a dynamic current distribution. The communication system in which the C-and D-CNNs are embedded is discussed