Experimental Results of a Michigan-like Evolution Strategy for Non-stationary Clustering
Non-stationary clustering deals with the clustering of a sequence of data samples obtained at a diverse time instant. A paradigm case of non-stationary clustering is the color quantization of image sequences. We propose an efficient evolution strategy to compute adaptively the color representatives for each image in the sequence.
KeywordsEvolution Strategy Mutation Operator Vector Quantization Cluster Problem Image Quantization
Unable to display preview. Download preview PDF.
- T. Back and H.P. Schwefel. Evolutionary computation: an overview. In IEEE Int. Conf. Evolutive Computation, pages 20–29, 1996.Google Scholar
- E. Diday and J.C. Simon. Clustering Analysis, In K.S. Fu (editor), Digital Pattern Recognition, pages 47–94. Springer Verlag, 1980.Google Scholar
- R.D. Duda and P.E. Hart. Pattern Classification and Scene Analysis. John Wiley, Chichester, 1973.Google Scholar
- K. Fukunaga. Statistical Pattern Recognition. Academic Press, 1990.Google Scholar
- A. Gersho and R.M. Gray. Vector Quantization and signal compression. Kluwer Academic Publisher, 1992.Google Scholar
- Y. Gong, H. Zen, Y. Ohsawa, and M. Sakauchi. A color video image quantization method with stable and efficient color selection capability. In Int. Conf. Pattern Recognition, volume 3, pages 33–36, 1992.Google Scholar
- A.K. Jain and R.C. Dubes. Algorithms for clustering data. Prentice Hall, 1988.Google Scholar
- Z. Michalewicz. Evolutionary computation: practical issues. In IEEE Int. Conf. Evolutive Computation, pages 30–39, 1996.Google Scholar
- X. Wu. Efficient Statistical Computations for Optimal Color Quantization, pages 126–133. Academic Press Professional, 1991.Google Scholar