Contextual Classification Of Remotely Sensed Data Using Frequency-Based Approach

Remote sensing sensors are now able to deliver greatly increased amount of information. 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 spatial contextual information. In this paper, we shall present a contextual classification method based on a frequency-based approach for the purposes of land cover mapping. Additionally, classification maps are produced which have significantly less speckle error.