This paper presents the design of a new clustering algorithm for images having wide range of variations in appearances and shape. The major chore of the clustering process involves in creating the partitions, reassigning the elements of the partitions and identifying the compact cluster obtained. The clusters are created from various low-dimensional spaces of the data set. Hierarchically related eigenspaces are employed to reassign the elements of the cluster. The clusters obtained from the proposed clustering scheme are used to form the learning set of the classification module. The quality of clusters generated is evaluated from the classification results. Comparisons on the clustering performance have been made with the well-known K-means and nearest neighbor-based clustering techniques. Excellent performance of the proposed clustering scheme is proved from the results reported. The benchmark datasets for objects and faces having images with large pose variations have been used to illustrate the efficiency and effectiveness of the proposed scheme.
展开▼
