Canberra Distance based Approach for Classifying Remote Sensing Images using Affinity Propagation

Clustering is the process of subdividing an input data set into a desired number of subgroups so that members of the same subgroup are similar and members of different subgroups have diverse properties. Many heuristic algorithms have been applied to the clustering problem, which is known to be NP Hard. This paper represents a frame work for clustering on image data. The objective of the frame work algorithm used to perform clustering on very large data sets, especially on Remote sensing image data sets. Efficient time techniques are used as a performance measure for clustering on image data.