Design of Associative Memory for Gray-Scale Images by Multilayer Hopfield Neural Networks

In this paper a new design procedure for Hopfield associative memories storing grey-scale images is presented. The proposed architecture, with both intra-layer and inter-layer connections, is an evolution of a previous work based on the decomposition of the image with 2L gray levels into L binary patterns, stored in L uncoupled neural networks: that allows to store images with the commonly used number of 256 gray levels. The learning algorithm, used to store the binary images, guarantees asymptotic stability of the stored patterns, has a low computational cost, and allows to control the precision of the connection weights.