Satellite Image Classification Using Cascaded Architecture of Neural Fuzzy Network - Advanced Techniques in Knowledge Discovery and Data Mining - page 210

8. Satellite Image Classification Using Cascaded
Architecture of Neural Fuzzy Network
Chin-Teng Lin, Her-Chang Pu, and Yin-Cheung Lee
Department of Electrical and Control Engineering, National Chiao-Tung Uni-
versity, Hsinchu, Taiwan, R.O.C.
Because satellite images usually contain many complex factors and mix-up sam-
ples, a high recognition rate is not easy to attain. Especially for a nonhomogene-
ous region, the gray values of its satellite image vary greatly, and thus the direct
use of gray values cannot do the categorization task correctly. Classification of
terrain cover using polarimetric radar is an area of considerable current interest
and research. Without the benefit of satellite, we cannot analyze the information of
the distribution of soils and cities for a land development, as well as the variation
of clouds and volcano for weather forecasting and for precaution, respectively.
This chapter discusses a hybrid neural fuzzy network, combining unsupervised
and supervised learning, for designing classifier systems. Based on systematic
feature analysis, which is crucial for data mining and knowledge extraction, the
proposed scheme signifies a novel algebraic system identification method, which
can be used for knowledge extraction in general, and for satellite image analysis in
particular. The goal of this chapter is to develop a cascaded architecture of a neural
fuzzy network with feature mapping (CNFM) to help the classification of satellite
images.
8.1 Introduction
This chapter discusses a hybrid neural fuzzy network combining unsupervised and
supervised learning for designing classifier systems. Based on systematic feature
analysis, which is crucial for data mining and knowledge extraction [1], [2], [3],
[4], the proposed scheme signifies a novel algebraic system-identification method,
which can be used for knowledge extraction in general and for satellite image
analysis in particular.
Classification of terrain cover using polarimetric radar is an area of consider-
able current interest and research. Without the benefit of satellite, we cannot ana-
lyze the information of the distribution of soils and cities for land development, as
well as the variation of clouds and volcano for weather forecasting and precaution,
respectively. However, one cannot talk about these applications without mention-
ing the classification. Our motivation is to build up a system that can assist us in
analyzing and classifying the information from satellite images automatically.
Early investigations for satellite-image classification have employed autocor-
relation functions [5], power spectra, relative frequencies of various gray levels on
the unnormalized image [6], and the second-order gray-level statistics method [7]
to obtain texture features. These applications should be extended to proceed the