Manhattan Distance Based Affinity Propagation Technique for Clustering in Remote Sensing Images

Cluster analysis partitions a dataset into a reasonable number of disjoint groups, where each group contains similar patterns. Due to a high number of spectral channels hyper Remote Sensing are difficult to classify with high accuracy and efficiency. In this paper we propose a new image clustering method MD-AP( Manhattan Distance Based Affinity Propagation) for extract the Land cover Classification with High Accuracy and Less Computation Time for Comparing the convention methods like K-Means Clustering Algorithm.