Segmentation of remote-sensing images by artificial neural networks

A novel unsupervised incremental neural network (Turkish acronym - DAYS) is proposed for the segmentation of remote-sensing images. Feature vectors are formed by the intensity of one pixel of each channel. The training set of a DAYS network is formed using all pixels of the image. The remote-sensing image is segmented according to the decision of the network. In the study, the segmentation results of DAYS and Kohonen networks are compared.