Computer Science and Engineering, Department of


Date of this Version



Published in IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, VOL. 37, NO. 2, MARCH 1999. Digital Object Identifier: 10.1109/36.752194 Copyright 1999 IEEE. Used by permission.


In this paper, we describe a segmentation technique that integrates traditional image processing algorithms with techniques adapted from knowledge discovery in databases (KDD) and data mining to analyze and segment unstructured satellite images of natural scenes. We have divided our segmentation task into three major steps. First, an initial segmentation is achieved using dynamic local thresholding, producing a set of regions. Then, spectral, spatial, and textural features for each region are generated from the thresholded image. Finally, given these features as attributes, an unsupervised machine learning methodology called conceptual clustering is used to cluster the regions found in the image into N classes—thus, determining the number of classes in the image automatically.We have applied the technique successfully to ERS-1 synthetic aperture radar (SAR), Landsat thematic mapper (TM), and NOAA advanced very high resolution radiometer (AVHRR) data of natural scenes.