A fast algorithm for high quality vector quantization codebook design

  • Carlo Braccini
  • Fabio Cocurullo
  • Fabio Lavagetto
Image Coding II
Part of the Lecture Notes in Computer Science book series (LNCS, volume 974)


In this paper we present a new theoretical approach to the problem of optimal Vector Quantization. We base, in fact, our method on the a priori explicit analysis of the effects on the MSE distortion introduced by an arbitrary exchange of training vectors among clusters. Even when the theoretical results corresponding to the simplest possible case are used, the proposed algorithm outperforms the GLA method to an impressive extent both in speed and in performance. Experiments on different images from the USC database have proved that the proposed algorithm is 5 to 10 times faster than the GLA method increasing the convergence Peak Signal to Noise Ratio (PSNR) of up to 1.12 dB.


  1. 1.
    A. Gersho, R.M. Gray, Vector Quantization and Signal Compression, Kluwer Academic Publishers, 1992.Google Scholar
  2. 2.
    J. Max, Quantizing for Minimum Distortion, IRE Trans. on Inf. Theory, Vol. IT-6, 1960, pp. 7–12.Google Scholar
  3. 3.
    R.M. Gray, E. Karnin, Multiple Local Optima in Vector Quantizers, IEEE Trans. on Inf. Theory, Vol. IT-28, 1982, pp. 256–261.Google Scholar
  4. 4.
    J.H. Conway, N.J.A. Sloane, Voronoi Regions of Lattices 2-nd Moments of Polytopes and Quantization, IEEE Trans. on Inf. Theory, Vol. IT-28, 1982, pp. 211–226.Google Scholar
  5. 5.
    W.H. Equitz, A New Vector Quantization Clustering Algorithm, IEEE Trans. Acoust. Speech Signal Processing, vol. 37, no. 10, Oct. 1989.Google Scholar
  6. 6.
    Chok-Ki Chan and Chi-Kit Ma, A Fast Method of Designing Better Codebooks for Image Vector Quantization, IEEE Trans. on Communications, Vol. 42, No. 2/3/4, Feb./Mar./Apr. 1994.Google Scholar
  7. 7.
    F. Cocurullo, F. Lavagetto and M. Moresco, Optimal Clustering for Vector Quantizer Design, Proc. EUSIPCO-92 Brusseles, Begium, August 24–27, Vol. I, pp. 563–566.Google Scholar
  8. 8.
    F. Cocurullo and F. Lavagetto, A New Algorithm for Vector Quantization, to appear in Proc. Data Compression Conference — DCC '95 Snowbird, Utah, March 28–30, 1995.Google Scholar
  9. 9.
    A. Gersho, On the Structure of Vector Quantizers, IEEE Trans. on Inf. Theory, Vol. IT-28, 1982, pp. 157,166.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1995

Authors and Affiliations

  • Carlo Braccini
    • 1
  • Fabio Cocurullo
    • 1
  • Fabio Lavagetto
    • 1
  1. 1.University of GenovaItaly

Personalised recommendations