An application of the Self Organizing Map Algorithm to computer aided classification of ASTER multispectral data

In this paper we employ the Kohonen’s Self Organizing Map (SOM) as a strategy for an unsupervised analysis of ASTER multispectral (MS) images. In order to obtain an accurate clusterization we introduce as input for the network, in addition to spectral data, some texture measures extracted from IKONOS images, which gives a contribution to the classification of manmade structures. After clustering of SOM outcomes, we associated each cluster with a major land cover and compared them with prior knowledge of the scene analyzed.