Abstract
The ultimate goal of vector quantization (VQ) is to encode the signal into representative code vectors such that it can be represented digitally in a compact way. This task can be formulated as an optimization problem, namely the minimization of the total distance between the signal and the code vectors. In this paper, we formulate VQ as a constrained binary integer programming problem by eliminating the code vectors, where the constraints that partition the signal space are linear. We propose a two dimensional Gradient Network to solve this problem. The performance of this solution method is tested on image compression applications and the results are compared with the ones obtained by the well-known k-means algorithm.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Ahalt S.C., Fowler J.E.: Vector Quantization using Artificial Neural Network Models. Proceedings of The Int. Workshop on Adaptive Methods and Emergent Techniques for Signal Processing and Communications. (1993) 42–61
Gray R.M., Neuhoff D.L.: Quantization. IEEE Transactions on Information Theory, Vol. 44, No. 6. (1998) 2325–2383
Smith K.A.: Neural Networks for Combinatorial Optimization A Review of More Than A Decade Research. Informs Journal on Computing, Vol.11, No. 1. (1999)
Kamgar-Parsi B., Gualtieri J.A, Devaney J. E., Kamgar-Parsi B.: Clustering with Neural Networks. Biological Cybernetics 6, (1990) 201–208
Kamgar-Parsi B., Kamgar-Parsi B.: On Problem Solving with Hopfield Neural Networks. Biological Cybernetics 62, (1990) 415–523
Doğan H., Güzeliş C.: VQ As an Integer Optimization Problem and Gradient Artificial Neural Network Solution (In Turkish). Proceeding of SIU2002, (2002) 266–271
Joya G., Atencia M.A., Sandoval F.: Hopfield Neural Networks for Optimization Study of The Different Dynamics. Neurocomputing Vol. 43, (2002) 219–237
Sammouda R., Noboru N., Nishitani H.: A Comparison of Hopfield Neural Network and Boltzmann Machine in Segmenting MR Images of the Brain. IEEE Transactions on Nuclear Science, Vol. 43, No. 6 (1996) 3361–3369
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Doğan, H., Güzeliş, C. (2003). A Gradient Network for Vector Quantization and Its Image Compression Applications. In: Kaynak, O., Alpaydin, E., Oja, E., Xu, L. (eds) Artificial Neural Networks and Neural Information Processing — ICANN/ICONIP 2003. ICANN ICONIP 2003 2003. Lecture Notes in Computer Science, vol 2714. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44989-2_66
Download citation
DOI: https://doi.org/10.1007/3-540-44989-2_66
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40408-8
Online ISBN: 978-3-540-44989-8
eBook Packages: Springer Book Archive