Fast algorithm for VQ codebook design

Abstract

The paper presents a fast codebook training algorithm for vector quantisation. It uses an elimination rule, based on triangular inequality criteria, as well as the partial distortion elimination method, to relieve the computational burden of a conventional codebook training algorithm, including a binary codeword splitting algorithm for the initial codebook and the LBG recursive algorithm. Over 95%savings in both multiplication and addition operations were achieved in the simulation of a VQ codebook training of a ‘Lena’ image using 16-dimensional vectors.