A grid-density based technique for finding clusters in satellite image

High resolution and high dimensional satellite images cause problems for clustering methods due to clusters of different sizes, shapes and densities as they contain huge amount of data. Due to this reason, most algorithms for clustering satellite data sacrifice the correctness of their results for fast processing time. The processing time may be greatly influenced by the use of grids. In this paper, we propose a grid density based clustering method for detecting the clusters present in satellite images. The clustering is based on both the band values as well as the texture features in the satellite images. Experimental results are presented to establish the efficiency of this technique in detecting the clusters present in satellite images.

► In this study, we use a grid density based technique to cluster multi-spectral satellite images. ► The spectral bands and the texture feature vectors are together used to detect clusters in the image data. ► The cluster quality is dependent on the size of the grid and the user defined parameters used.