Clustering is used to organize data for efficient retrieval. A popular technique for clustering is based on k-Means such that the data is partitioned into k clusters. In k-Means clustering a set of n data points in d-dimensional space Rd, an integer k is given and the problem is to determine a set of k-points in Rd called centers, to minimize the mean squared distance from each point to its nearest center. In this method, the number of clusters is predefined and the technique is highly dependent on the initial identification of elements that represent the clusters well. A large area of research in clustering has focused on improving the clustering process such that the clusters are not dependent on the initial identification of cluster representation. In this paper, a modified technique, which grows the clusters without the need to specify the initial cluster representation, has been proposed. Initially a local search single swap heuristic can identify the number of clusters and its centers in the interpolated (bicubic) multispectral image. Then the regular k-Means clustering is implemented using the results of the previous process for the true image data set. The technique achieves an impressive speed up of the clustering process even when the number of clusters is not specified initially and the classification accuracy is improved within a fewer number of iterations.
Artificial Neural Networks have gained increasing popularity as an alternative to statistical methods for classification of remote sensed images. The superiority of neural networks is that, if they are trained with representative training samples they show improvement over statistical methods in terms of overall accuracies. However, if the distribution functions of the information classes are known, statistical classification algorithms work very well. To retain the advantages of both the classifiers, decision fusion is used to integrate the decisions of individual classifiers. In this paper a new unsupervised neural network has been proposed for the classification of multispectral images. Classification is initially achieved using Maximum Likelihood and Minimum-Distance-to-Means classifier followed by neural network classifier and the decisions of these classifiers are fused in the decision fusion center implemented using Majority-Voting technique. The results show that the scheme is effective in terms of increased classification accuracies (98%) compared to the conventional methods.