Using an enhanced LBG algorithm to reduce the codebook error in vector quantization

Presents a modification of the well-known LBG (Linde, Buzo and Gray, 1980) algorithm for the generation of codebooks in vector quantization. Our algorithm, which we call the ILBG (iterated LBG) algorithm, reduces the codebook error of the LBG algorithm drastically in typical applications. In our experiments, we were able to achieve up to a 75% reduction of the codebook error in only a few additional iteration steps. In the context of lossy image compression, this error reduction in turn leads to an increase of 2-3 dB in the peak signal-to-noise ratio (PSNR).