MULTISPECTRAL CLASSIFICATION OF LANDSAT-IMAGES USING NEURAL NETWORKS

Recent progress in neural network research has demonstrated the usefulness of neural networks in a variety of areas. In this work we report the application of three-layer back-propagation networks for classification of Landsat TM data on a pixel-by-pixel basis. The results are compared to Gaussian maximum likelihood classification. First, we show that the neural network is able to perform better than the maximum likelihood classifier. Secondly, in an extension of the basic network architecture we show that textural information can be integrated into the neural network classifier without the explicit definition of a texture measure. Finally, we examine the use of neural networks for postclassificational smoothing.