Investigations into the analysis of remote sensing images with a growing neural gas pattern recognition algorithm

The growing neural gas (GNG) pattern recognition algorithm is an unsupervised algorithm which inserts nodes into the state space of the training data. Observations of the behavior of the algorithm lead to the hypothesis that this method may be an efficient pre-classification clustering algorithm for data in highly discrete state spaces, as in satellite remote sensing images. The GNG algorithm was used to train a network using a Landsat image from Wyoming. The initial results of this investigation were extremely positive. The image derived from the trained GNG network is difficult to distinguish from the source image. Preliminary statistical results also indicate a high degree of correlation between the source and resultant images.