Fuzzy decision tree model adaptation to multi- and hyperspectral imagery supervised classification

Now the land cover classification system is very important for various remote sensing applications and many sectors of economy. Therefore, development of algorithms for multi- and hyperspectral imagery classification is an urgent task. In this paper we present a new efficient algorithm for multi- and hyperspectral imagery classification based on fuzzy decision tree approach. We use the multispectral imagery spectral bands as fuzzy data source attributes and cumulative mutual information between them and the resulting fuzzy classification as decision tree inducing criterion. Proposed algorithm provides classification accuracy than traditional ones and significant data dimensionality reduction by means of informative spectral bands selection.