The application of self-organizing feature maps to image vector quantization (VQ) is considered. Their property of ordering, which is absent in conventional vector quantizers, can be used in order to improve the quality of the quantized images or to simplify the VQ process. A differential coding technique is presented which exploits the correlation between addresses relating to adjacent blocks. An algorithm is proposed for the evaluation of a "first guess" codeword, which can improve the performance of some fast search algorithms as the partial distance scheme.
展开▼