A COMPARISON OF EXPERIMENTAL RESULTS WITH AN EVOLUTION STRATEGY AND COMPETITIVE NEURAL NETWORKS FOR NEAR REAL-TIME COLOR QUANTIZATION OF IMAGE SEQUENCES

Color quantization of image sequences is a case of non-stationary clus tering problem. The approach we adopt to deal with this kind of proble ms is to propose adaptive algorithms to compute the cluster representa tives. We have studied the application of Competitive Neural Networks and Evolution Strategies to the one-pass adaptive solution of this pro blem. One-pass adaptation is imposed by the near real-time constraint that we try to achieve. In this paper we propose a simple and effectiv e evolution strategy for this task. Two kinds of competitive neural ne tworks are also applied. Experimental results show that the proposed e volution strategy can produce results comparable to that of competitiv e neural networks.