Multispectral Classification of Spot Imagery Using Unsupervised Neural Network
C.F.Chen* S.D.Shyn** S.W.Chen***
Abstract
This paper present a two-stage approach to classify remotely sensed imagery. At the first stage, an unsupervised adaptiv resonance theory neural network is invoked to perform a multi-spectral classification of satellite images. The outcome of this stage is a set of fine spectral classes. Since our goal is to obtain meaningful classes of the images, the fine spectral classes. are, at the second stage, reorganized into a small set of meaningful classes usimg a statistical clustering technique. The efficiency and accuracy of the proposed method is examined using a synthetic image. Afterwards, the proposed classifier is applied to a real SPOT image. Compared to another unsupervised classifier of ISOCLS, both classifiers have compatible processing times. While our has achieved a better accuracy (96% for ours and 94% for ISOCLS).
Keywords:
Two-stage unsupervised classifier, Adaptive resonance theory neural networks, statistical clustering techniques.
*Center for Space and Remote Sensing Research, National Central University
**Center for Space and Remote Sensing Research, National Central University
***Dept. of Information and Computer Education, National Central University