PCA-BASED SEEDING FOR IMPROVED VECTOR QUANTIZATION

G. Knittel, R. Parys

Abstract

We propose a new method for finding initial codevectors for vector quantization. It is based on Principal Component Analysis and uses error-directed subdivision of the eigenspace in reduced dimensionality. Addi-tionally, however, we include shape-directed split decisions based on eigenvalue ratios to improve the visual appearance. The method achieves about the same image quality as the well-known k-means++ method, while providing some global control over compression priorities.

References

  1. Arthur, D., Vassilvitskii, S., 2007. k-means++: the advantages of careful seeding. In Proc. 18th annual ACMSIAM symposium on discrete algorithms, pages 1027- 1035.
  2. Barbakh, W., Fyfe, C., 2008. Clustering with alternative similarity functions. In Proc. 7th WSEAS Int. Conf. on Artificial Intelligence, Knowledge Engineering and Data Bases, pages 238-244.
  3. Bradley, P. S., Fayyad, U., 1998. Refining initial points for K-means clustering. In Proc. 15th Int. Conf. on Machine Learning, pages 91-99.
  4. Fritzke, B., 1997. The LBG-U method for vector quantization - an improvement over LBG inspired from neural networks. In Neural Processing Letters, Vol. 5, No. 1, pages 35-45.
  5. Gray, R. M., 1984. Vector quantization. In IEEE ASSP Magazine, Vol. 1, No. 2, (1984), pages 4-29.
  6. Gersho, A., Gray, R. M., 1992. Vector quantization and signal compression, Kluwer Academic Publishers.
  7. Lloyd, S. P., 1982. Least squares quantization in PCM. In IEEE Trans. on Information Theory, Vol. 28, 1982, pages 129-137.
  8. Ostrovsky, R., Rabani, Y., Schulman, L., Swamy, C., 2006. The Effectiveness of Lloyd-Type Methods for the k-Means Problem. In Proc. 47th Annual IEEE Symposium on Foundations of Computer Science (FOCS'06), pages 165-176.
  9. Pena, J. M., Lozano, J. A., Larranaga, P., 1999. An empirical comparison of four initialization methods for the kmeans algorithm. Pattern Recognition Lett., Vol. 20, No. 10, pages 1027-1040.
Download


Paper Citation


in Harvard Style

Knittel G. and Parys R. (2009). PCA-BASED SEEDING FOR IMPROVED VECTOR QUANTIZATION . In Proceedings of the First International Conference on Computer Imaging Theory and Applications - Volume 1: IMAGAPP, (VISIGRAPP 2009) ISBN 978-989-8111-68-5, pages 96-99. DOI: 10.5220/0001808100960099


in Bibtex Style

@conference{imagapp09,
author={G. Knittel and R. Parys},
title={PCA-BASED SEEDING FOR IMPROVED VECTOR QUANTIZATION},
booktitle={Proceedings of the First International Conference on Computer Imaging Theory and Applications - Volume 1: IMAGAPP, (VISIGRAPP 2009)},
year={2009},
pages={96-99},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001808100960099},
isbn={978-989-8111-68-5},
}


in EndNote Style

TY - CONF
JO - Proceedings of the First International Conference on Computer Imaging Theory and Applications - Volume 1: IMAGAPP, (VISIGRAPP 2009)
TI - PCA-BASED SEEDING FOR IMPROVED VECTOR QUANTIZATION
SN - 978-989-8111-68-5
AU - Knittel G.
AU - Parys R.
PY - 2009
SP - 96
EP - 99
DO - 10.5220/0001808100960099