Neural network approach for adaptive vector quantization

The problem of adaptive vector quantization (VQ) for image sequence coding is addressed. The goal of this work is to overcome the limits that reduce the possibility of a hardware implementation of the schemes already presented in the literature. The limits principally concern the complexity of the implementation in real time of the classical Linde-Buzo-Gray (LBG) algorithm, which is necessary to introduce some adaptive capabilities in a VQ. Neural network methods, because of their fast codebook design, seem an interesting alternative to solve this problem. The authors have used an unsupervised neural network approach to introduce adaptivity in a vector quantizer by using a codebook replenishment method. The proposed adaptive VQ algorithm has been tested in a motion compensated interframe image coding scheme. The results of the simulations are very promising. A considerable rise of the coder performance with respect to the use of fixed VQ has been obtained