Adaptive Classification of Hyperspectral Image

An important problem in pattern recognition is the effect of limited training samples on classification performance. When the ratio of the number of training samples to the dimensionality is small, parameter estimates become highly variable, causing the deterioration of classification performance. This problem has become more prevalent in remote sensing with the emergence of a new generation of sensors. While the new sensor technology provides higher spectral and spatial resolution, enabling a greater number of spectrally separable classes to be identified, the needed labeled samples for designing the classifier remain difficult and expensive to acquire. In this paper, we propose an adaptive classification model that operates based on decision fusion. This method uses soft learning strategy. In this classifier, learning is performed at two steps. At the beginning of this method, observation space is parted and several groups of bands are produced. After providing the primary decisions, several rules are used in decision fusion center to determine the final class of pixels. Reported results on remote sensing images show classification performance is improved, and this method may solve the limitation of training samples in the high dimensional data and the Hughes phenomenon may be mitigated.