Image texture classification using a multiagent genetic clustering algorithm

Based on texture features, we propose an unsupervised image classification method by using a novel evolutionary clustering technique, namely multiagent genetic clustering algorithm (MAGAc). In MAGAc, the clustering problem is considered from an optimization viewpoint. Each agent is a matrix of real numbers representing the cluster centers. Agents interact with others under the pressure of environment to search the best partition of data. After extracting texture features from an image, MAGAc determines the partition of feature vectors using evolutionary search. In experiments, six UCI datasets and four artificial textural images are used to test the performance of MAGAc. The experimental results show that in terms of cluster quality, MAGAc outperforms the K-means algorithm and a genetic algorithm-based clustering technique.