Clustering is the process of discovering groups within the data, based on similarities, with a minimal, if any, knowledge of their structure. The self-organizing (or Kohonen) map (SOM) is one of the best known neural network algorithms. It has been widely studied as a software tool for visualization of high-dimensional data. Important features include information compression while preserving topological and metric relationship of the primary data items. Although Kohonen maps had been applied for clustering data, usually the researcher sets the number of neurons equal to the expected number of clusters, or manually segments a two-dimensional map using some a priori knowledge of the data. This paper proposes techniques for automatic partitioning and labeling SOM networks in clusters of neurons that may be used to represent the data clusters. Mathematical morphology operations, such as watershed, are performed on the U-matrix, which is a neuron-distance image. The direct application of watershed leads to an oversegmented image. It is used markers to identify significant clusters and homotopy modification to suppress the others. Markers are automatically found by performing a multi-level scan of connected regions of the U-matrix. Each cluster of neurons is a sub-graph that defines, in the input space, complex and nonparametric geometries which approximately describes the shape of the clusters. The process of map partitioning is extended recursively. Each cluster of neurons gives rise to a new map, which are trained with the subset of data that were classified to it. The algorithm produces dynamically a hierarchical tree of maps, which explains the cluster's structure in levels of granularity. The distributed and multiple prototypes cluster representation enables the discoveries of clusters even in the case when we have two or more non-separable pattern classes.4384 1627Vinod, V.V., Chaudhury, S., Mukherjee, J., Ghose, S., A connectionist approach for clustering with applications in image analysis (1994) IEEE Trans. Systems, Man & Cybernetics, 24 (3), pp. 356-384Costa, J.A.F., (1999) Automatic classification and data analysis by self-organizing neural networks, , Ph.D. Thesis. State University of Campinas, SP, BrazilEveritt, B.S., (1993) Cluster Analysis, , Wiley: New YorkKaufman, L., Rousseeuw, P., (1990) Finding Groups in Data: An Introduction to Cluster Analysis, , Wiley: New YorkSu, M.-C., Declaris, N., Liu, T.-K., Application of neural networks in cluster analysis (1997) Proc. of the 1997 IEEE Intl. Conf. on Systems, Man, and Cybernetics, pp. 1-6Kothari, R., Pitts, D., On finding the number of clusters (1999) Pattern Recognition Letters, 20, pp. 405-416Hardy, A., (1996) On the number of clusters. Computational Statistics and Data Analysis, 23, pp. 83-96Jain, A.K., Murty, M.N., Flynn, P.J., Data clustering: A review (1999) ACM Computing Surveys, 31 (3), pp. 264-323Ball, G., Hall, D., A clustering technique for summarizing multivariate data (1967) Behavioral Science, 12, pp. 153-155Bezdek, J.C., Pal, N.R., Some new indexes of cluster validity (1998) IEEE Transactions on Systems, Man, and Cybernetics (Part B), 28, pp. 301-315Haykin, S., (1999) Neural Networks: A Comprehensive Foundation, , 2nd edition, Prentice-Hall: New YorkKamgar-Parsi, B., Gualtieri, J.A., Devaney, J.E., Kamgar-Parsi, B., Clustering with neural networks (1990) Biological Cybernetics, 63, pp. 201-208Frank, T., Kraiss, K.-F., Kuhlen, T., Comparative analysis of fuzzy ART and ART-2A network clustering performance (1998) IEEE Trans. on Neural Networks, 9, pp. 544-559Kohonen, T., (1997) Self-Organizing Maps, , 2nd Ed., Springer-Verlag: BerlinUltsch, A., Self-Organizing Neural Networks for Visualization and Classification (1993) Information and Classification, pp. 301-306. , O. Opitz et al. (Eds)., Springer: BerlinGirardin, L., (1995) Cyberspace geography visualization, , heiwww.unige.ch/girardin/cgvGonzales, R.C., Woods, R.E., (1992) Digital Image Processing. Reading, , MA: Addison-WesleyBarrera, J., Banon, J., Lotufo, R., Mathematical Morphology Toolbox for the Khoros System (1994) Image Algebra and Morphological Image Processing V, 2300, pp. 241-252. , E. Dougherty et al. Eds. Proc. SPIESerra, J., (1982) Image Analysis and Mathematical Morphology, , Academic Press: LondonNajman, L., Schmitt, M., Geodesic Saliency of Watershed Contours and Hierarchical Segmentation (1996) IEEE Trans. on Pattern Analysis and Machine Intelligence, 18, pp. 1163-1173Bleau, A., Leon, L.J., Watershed-based segmentation and region merging Comp. Vis. Image Underst., 77, pp. 317-370Costa, J.A.F., Mascarenhas, N., Netto, M.L.A., Cell nuclei segmentation in noisy images using morphological watersheds (1997) Applications of Digital Image Processing XX., 3164, pp. 314-324. , A. Tescher Ed. Proc. of the SPIECosta, J.A.F., Netto, M.L.A., Estimating the Number of Clusters in Multivariate Data by Self-Organizing Maps (1999) International Journal of Neural Systems, 9 (3), pp. 195-202Costa, J.A.F., Netto, M.L.A., Cluster analysis using self-organizing maps and image processing techniques Proc. of the 1999 IEEE Intl. Conf. on Systems, Man, and Cybernetics, , Tokyo, JapanNakamura, E., Kehtarnavaz, N., Determining the number of clusters and prototype locations via multi-scale clustering (1998) Pattern Recognition Letters, 19, pp. 1265-1283Li, T., Tang, Y., Suen, S., Fang, L., Hierarchical classification and vector quantisation with neural trees (1993) Neurocomputing, 5, pp. 119-139Racz, J., Klotz, T., Knowledge representation by dynamic competitive learning techniques Proc. SPIE, 1469, pp. 778-783Adams, R., Butchart, K., Davey, N., Hierarchical classification with a competitive evolutionary neural tree (1999) Neural Networks, 12, pp. 541-551Costa, J.A.F., Netto, M.L.A., Automatic Data Classification by a Hierarchy of Self-Organizing Maps Proc. 1999 IEEE Intl. Conf. on Systems, Man, and Cybernetics, , Tokyo, JapanKoikkalainen, P., Progress with the Tree-Structured Self-Organizing Map (1994) Proc. of the 11 th European Conference on Artificial Intelligence, pp. 211-215Miikkulainen, R., Script Recognition with Hierarchical Feature Maps (1990) Connection Science, pp. 83-101