Satellite Images Scene Classification Based Support Vector Machines and K-Nearest Neighbor

Abstract

Satellite image classification is a valuable technique for producing worthy information. This paper deal with high-resolution satellite for scene classification. In this research presents three algorithms were used to extract the features which are local binary patterns, gray level co occurrence matrix, and color histogram features. The classification process included the use of two types of data mining techniques belongs to supervisor classification which are support vector machines, and k-nearest neighbor. Test results explain that the proposed classification method obtains a very auspicious performance.