Classification of Multispectral satellite images

This paper is a review of classification of remote sensed Multispectral satellite images. Texture is the frequency of tonal changes on the image. The texture gives the `rough´ or `smooth´ appearance of the image. Higher resolution causes higher spectral variability within a class and lessens the statistical separability among different classes in a traditional pixel-based classification. Several methods of image classification exist and a number of fields apart from remote sensing like image analysis and pattern recognition make use of a significant concept.