Compression of subband-filtered images via neural networks

A novel architecture for image compression is proposed, which is based on a suitable combination of subband filtering and linear neural networks. This combination permits efficient coding, together with the advantages of the neural-network-based approach. The architecture is described, and results of simulations are presented. The architecture is shown to perform well, notwithstanding the reduced complexity of the approach. The structure is highly parallel, so that high computation rates are possible; this property can be useful if sequences of images are to be compressed.<>