Iterated Watersheds, A Connected Variation of K-Means for Clustering GIS Data

In this article, we propose a novel algorithm to obtain solution the clustering problem with an additional constraint of connectivity. This is achieved by suitably modifying K-Means include connectivity constraints. The modified involves repeated application watershed transform, and hence referred as iterated watersheds. Detailed analysis performed using toy examples. Iterated watersheds compared several image segmentation algorithms. It has been shown that performs better than methods such spectral clustering, isoperimetric partitioning, on various measures. To illustrate applicability - simple placing emergency stations suitable cost function considered. Using real world road networks cities, greedy K-center methods. observed result in 4 66 percent improvement over 31 72 Greedy K-Centers experiments cities.