K-means classification


Common image classification procedures can be broken down into two broad subdivisions based on the method used:

Programs, called clustering algorithms, are used to determine the natural (statistical) groupings or structures in the data. Here, the algorithm used in one known as K-means. This algorithm uses an iterative approach that minimizes the sum of distances from each object to its cluster centroid, over all clusters. This algorithm moves objects between clusters until the sum cannot be decreased further. The result is a set of clusters that are as compact and well-separated as possible. The lower part of the figure (below the Isolate classes) can be used to extract one or several computed classes, either as color images on mask files.

Copyright © <2010>, <Joaquim Luis>

Created with the Freeware Edition of HelpNDoc: Full featured Help generator