Remote sensing data analysis by Kohonen feature map and competitive learning

In this paper as a preprocessing of land use classifications, we use the Kohonen feature map (KFM) and the competitive learning (CL) to get the better training data set. At a first step, the KFM that takes the Landsat TM data as input is adopted to form a rough classification of the wide area based on the observed data. At the next step, the CL whose inputs are the weights of the KFM node data is carried out to determine the category of each node of the KFM. The first weight set of the CL is taken as the weights at the corner nodes of the KFM. The combination of the two neural network techniques enables us to determine the rough land-use of an object region automatically. After that, the classification results by the KFM and the CL are further classified into more fine items by using the backpropagation method. Finally, the classification results have been compared with other methods.