Neural Approach for TV Image Compression Using a Hopfield Type Network

Part of Advances in Neural Information Processing Systems 1 (NIPS 1988)

Bibtex Metadata Paper

Authors

Martine Naillon, Jean-Bernard Theeten

Abstract

A self-organizing Hopfield network has been developed in the context of Vector Ouantiza(cid:173) -tion, aiming at compression of television images. The metastable states of the spin glass-like network are used as an extra the Minimal Overlap storage resource using and Mezard 1987) to rule (Krauth learning the organization of the attractors. optimize The sel f-organi zi ng that we have scheme devised the generation of an in adaptive codebook for any qiven TV image.