Abstract
In this study, projected clustering is introduced to hyperspectral imagery for unsupervised classification. The main advantage of projected clustering lies in its ability to simultaneously perform feature selection and clustering. This framework also allows selection of different sets of dimensions (features/bands) for different clusters. This framework provides an effective way to address the issues associated with the high dimensionality of the data. Experiments are conducted on both synthetic and real hyperspectral imagery. For this purpose, projected clustering algorithms are implemented and compared with k-means and k-means preceded by principal component analysis. Preliminary analyses of studied algorithms on synthetic hyperspectral imagery demonstrate good results. For real hyperspectral imagery, only ORCLUS is able to produce acceptable results as compared to other unsupervised methods. The main concern lies with identification of right parameter settings. More experiments are required in this direction.
Acknowledgements
The authors would like to thank Prof. David A. Landgrebe of Purdue University and Prof. Paolo Gamba of University of Pavia for making available the hyperspectral image used in this study. We gratefully acknowledge the anonymous reviewers for their valuable comments and suggestions to improve the quality of the article. The first author [Anand Mehta] thankfully acknowledges the financial support from the MHRD, India.