Abstract

Remote sensing is one of the hottest topics of research, which intends to study or analyze a particular object in the topographic map. The monitoring and management is possible when it is possible to differentiate the objects in the satellite image. However, satellite image classification is not easy, as it consists of numerous minute details. In addition to this, the accuracy and faster execution of the classification system are significant factors. This article presents a satellite image classification system that is capable of differentiating between soil, vegetation and water bodies. To achieve the goal, we categorize the entire system into three major phases; they are satellite image pre-processing, feature extraction and classification. The initial phase attempts to denoise the satellite image by the adaptive median filter and the contrast enhancement is done by Contrast Limited Adaptive Histogram Equalization (CLAHE). As the satellite image possess many important features, this work extracts curvelet moments by applying curvelet transform. The feature vector is formed out of these curvelet moments and the ELM classifier is used to train these features. The performance of the proposed approach is observed to be satisfactory in terms of sensitivity, specificity, and accuracy.