ADAPTIVE VECTOR QUANTITATION FOR PICTURE CODING USING NEURAL NETWORKS

The paper presents applications of neural network algorithms to the de sign of an adaptive vector quantizer. Vector quantization has been app lied to the problem of displaying natural images with a reduced set of colors (colormap) and to the interframe coding of image sequences. Th e first step was to test classical Linde Buzo Gray (LGB), Self Organiz ing Feature Maps (SOFM) and Competitive Learning (CL) algorithms for t he codebook design. The best results for the reconstructed quality ima ge and the computational time are obtained using a CL algorithm with a new initialization strategy that solves the problem of underutilized nodes. An-adaptive vector quantization algorithm is proposed and teste d in a motion compensated image coder. The results of the simulations are very promising. In fact the coder performance, compared with that using a fixed VQ, is considerably improved and the subjective quality of the coded images is much better than that obtained using standard v ector quantization, especially when rapid motion is present in the sce ne.