The aim of this work is to analyze the applicability of crowding differential evolution to unsupervised clustering. The basic idea of this approach, interpreting the clustering problem as a multi-modal optimization one, is similar to that of unsupervised niche clustering proposed by Nasraoui et al.[10] but instead of evolving only the clusters centers and statistically estimating the other parameters (scales and orientation) we evolve both the centers and the scale parameters of the clusters. Moreover, to simplify the evolutionary process, especially in the case of high-dimensional data, we evolve only hyper-ellipsoids parallel with the axes. In order to describe rotated clusters we used a multi-center representation, i.e. the cluster is covered by several normally oriented hyper-ellipsoids. Besides the fact that it simplifies the evolutionary process this multi-center representation allows describing almost arbitrary shaped clusters. Preliminary experimental results suggest that the proposed approach ensures a reliable identification of clusters in noisy data providing in the same time multi-center synthetic descriptions for them.