Cellular Neural Networks as Associative Memories Storing Grey-Scale Images

In this paper, we introduce an associative memory storing grey scale images. It is based on a suitable translation of the grey scale image into binary image, stored in a single binary Cellular Neural Network (CNN). The power of this particular neural network do resides in its local connectivity, very appreciable in VLSI implementation. The chosen learning algorithm guarantees asymptotic stability of the stored patterns, low computational cost, and control of the connection weights precision, without multiplication.