A new cluster tendency assessment method for fuzzy co-clustering in hyperspectral image analysis

The assessment of cluster tendency is a method determining whether a considering data-set contains meaningful clusters. The raised questions often are: How many clusters is the data-set reasonably partitioned into and How is the data-set disposed? In this paper, we proposed a new assessment method of cluster tendency which is called Silhouette-Based Assessment of Cluster Tendency (SACT). The SACT algorithm appraises the cluster tendency of the data-set in terms of the number of clusters and the initial prototypes which can be used to simultaneously determine the suitable number of clusters and the prototypes. The information of the suitable number of clusters and the prototypes helps the clustering algorithms to improve the performance. The hyperspectral image analysis is one of the complex problems which need to improve the speed of the SACT algorithm by using the Image Patch Distance technique for sparse hyperspectral image representation, i.e., reducing the size of the input data of the SACT algorithm. Experiments were conducted on some labeled synthetic data sets, color images and hyperspectral images. The proposed algorithm exhibited high performance, reliability and accuracy compared to previously algorithms in the assessment of cluster tendency.