Performances of Frequency-based Contextual Classifier in Land Use/Cover Classification using High Resolution Satellite Images

Remote sensing sensors are now able to deliver greatly increased amount of information with the used of high resolution sensor. But high or very high resolution sensors lead to noise in generally homogeneous classes as the data contains increased information with more internal variability. Conventional classification methods commonly cannot handle the complex landscape environment in the image. The result of each method has often "a salt and pepper appearances" which is a main characteristic of misclassification. It seems clear that information from neighboring pixels should increase the discrimination capabilities of the pixel based measured, and thus, improve the classification accuracy and the interpretation efficiency. This information is referred to as the spatial contextual information. In this paper, we shall present a contextual classification method based on a frequency-based approach for the purpose of land cover mapping. Additionally, classification maps are produced which have significantly less speckle error. In order to evaluate the performances of the classifier, 9 different window sizes ranging from 3x3 to 19x19 with an increment of 2 is tested.