Efficient LBG initialisation method for image vector quantisation

A simple initialisation method is proposed for the LBG VQ codebook design algorithm. Simulation results demonstrate that the proposed method achieves a faster convergence rate and a better local minimum than other existing LBG initialisation methods such as splitting and random guess.

[1]  Allen Gersho,et al.  Vector quantization and signal compression , 1991, The Kluwer international series in engineering and computer science.