Supervised and Unsupervised Clustering Based Dimensionality Reduction of Hyperspectral Data

Document Type : Original Article

Authors

Department of Photogrammetry and Remote Sensing, Faculty of Geodesy and Geomatics, K. N. Toosi University of Technology, Tehran, Iran

Abstract

Nowadays, hyperspectral images (HIs) are widely used for land cover land use (LCLU) mapping. Hyperspectral sensors collect spectral data in numerous adjacent spectral bands, which are usually redundant. Hyperspectral data processing comes with important challenges such as huge processing time, difficulties in transfer, and storage. In this study, two supervised and unsupervised dimensionality reduction methods are proposed for hyperspectral feature extraction based on the band clustering technique. In the first method, the unsupervised method, after the unsupervised band clustering stage with some statistical attributes, the principal component transform is used in each cluster, and the first PC component is considered an extracted feature. In the second method, the supervised method, bands are clustered based on training samples mean vectors of each class, and the weighted mean operator is used for feature extraction in each cluster. The experiment is conducted on the classification of real famous HI named Indian Pines. Comparing the obtained results and some other state of art methods proved the proposed method's efficiency.

Keywords


1.     Hughes, G, "On the mean accuracy of statistical pattern recognizers", IEEE Transactions on Information Theory, Vol. 14, 1, (1968), 55-63. DOI: 10.1109/TIT.1968.1054102
2.     Landgrebe, D., "Hyperspectral image data analysis",IEEE Signal Processing Magazine, Vol. 19, 1, (2002), 17-28. DOI: 10.1109/79.974718
3.     Lim, S., K.H. Sohn, and C. Lee. "Principal component analysis for compression of hyperspectral images", In IEEE International Geoscience and Remote Sensing Symposium,. IGARS S'01. (2001). DOI: 10.1109/IGARSS.2001.976068
4.     Harris, J. R., Rogge, D., Hitchcock, R., Ijewliw, O., Wright, D. "Mapping lithology in Canada's Arctic: application of hyperspectral data using the minimum noise fraction transformation and matched filtering", Canadian Journal of Earth Sciences, Vol. 42, 12, (2005),  2173-2193. DOI: 10.1139/e05-064
5.     Jia, X. and J.A. Richards, "Segmented principal components transformation for efficient hyperspectral remote-sensing image display and classification", IEEE Transactions on Geoscience and Remote Sensing, 1999. Vol. 37, 1, (1999), 538-542. DOI: 10.1109/36.739109
6.     Bioucas-Dias, J. M., Plaza, A., Camps-Valls, G., Scheunders, P., Nasrabadi, N., & Chanussot, J., "Hyperspectral remote sensing data analysis and future challenges",IEEE Geoscience and Remote Sensing Magazine, Vol. 1, 2, (2013), 6-36. DOI: 10.1109/MGRS.2013.2244672
7.     Datta, A., S. Ghosh, and A. Ghosh, "Unsupervised band extraction for hyperspectral images using clustering and kernel principal component analysis", International Journal of Remote Sensing, Vol 38, 3, (2017), 850-873. DOI: 10.1080/01431161.2016.1271470
8.     Fauvel, M., J. Chanussot, and J.A. Benediktsson. "Kernel principal component analysis for feature reduction in hyperspectral images analysis". IEEE  Proceedings of the 7th Nordic Signal Processing Symposium (2006). DOI: 10.1109/NORSIG.2006.275232
9.     Kaewpijit, S., J. Le Moigne, and T. El-Ghazawi, "Automatic reduction of hyperspectral imagery using wavelet spectral analysis", IEEE Transactions on Geoscience and Remote Sensing, 2003. Vol 41, 4, (2003), 863-871. DOI: 10.1109/TGRS.2003.810712
10.   Prabhu, N., M.K. Arora, and R. Balasubramanian, "Wavelet Based Feature Extraction Techniques of Hyperspectral Data", Journal of the Indian Society of Remote Sensing, Vol. 44, 3, (2016), 373-384. DOI: 10.1007/s12524-015-0506-9
11.   Hosseini, S.A. and H. Ghassemian. "A novel approach to hyperspectral data feature extraction using rational function curve fitting". IEEE International Conference on Signal and Image Processing Applications (ICSIPA), (2015). DOI: 10.1109/ICSIPA.2015.7412241
12.   Hosseini, S.A. and H. Ghassemian, "Rational function approximation for feature reduction in hyperspectral data", Remote Sensing Letters, Vol. 7, No. 2, (2016), 101-110. DOI: 10.1080/2150704X.2015.1101180
13.   Fukunaga, K., Introduction to statistical pattern recognition. 2013: Academic Press. Hardcover ISBN: 9780122698514
14.   David, L., "Hyperspectral image data analysis as a high dimensional signal processing problem", IEEE Signal Processing Magazin, Vol. 19, No. 1, (2002), 17-28. https://engineering.purdue.edu/~landgreb/SigProcPaper.pdf
15.   Baudat, G. and F. Anouar, "Generalized discriminant analysis using a kernel approach", Neural Computation, Vol. 12, No. 10, (2000) 2385-2404. DOI: 10.1162/089976600300014980
16.   Kuo, B.-C., C.-H. Li, and J.-M. Yang, "Kernel nonparametric weighted feature extraction for hyperspectral image classification", IEEE Transactions on Geoscience and Remote Sensing, Vol. 47, No. 4, (2009), 1139-1155. DOI: 10.1109/TGRS.2008.2008308
17.   Lee, C. and D.A. Landgrebe, Feature extraction based on decision boundaries. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 15, No. 4, (1993), 388-400. DOI: 10.1109/34.206958
18.   Kuo, B.-C. and D.A. Landgrebe, "Nonparametric weighted feature extraction for classification", IEEE Transactions on Geoscience and Remote Sensing,  Vol. 42, No. 5, (2004), 1096-1105. DOI: 10.1109/TGRS.2004.825578
19.   Asghari Beirami, B., and M. Mokhtarzade. "Introducing an unsupervised method for feature extraction of hyperspectral images using bands clustering in the prototype space." Journal of Geomatics Science and Technology, Vol. 9, No. 2 (2019), 195-207. http://jgst.issge.ir/article-1-907-en.pdf
20.   Esfandian, N., and K. Hosseinpourb. "A Clustering-Based Approach for Features Extraction in Spectro-Temporal Domain Using Artificial Neural Network." International Journal of Engineering, Transactions B: Applications, Vol. 34, No. 2 (2021): 452-457. DOI: 10.5829/IJE.2021.34.02B.17
21.   Mojaradi, B., Emami, H., Varshosaz, M., & Jamali, S. "A novel band selection method for hyperspectral data analysis", Int Arch Photogramm Remote Sens Spat Inf Sci, (2008).
22.   Mojaradi, B., Abrishami-Moghaddam, H., Zoej, M. J. V., & Duin, R. P. "Dimensionality reduction of hyperspectral data via spectral feature extraction", IEEE Transactions on Geoscience and Remote Sensing, Vol. 47, No. 7, (2009), 2091-2105. DOI: 10.1109/TGRS.2008.2010346
23.   Imani, M. and H. Ghassemian, "Band clustering-based feature extraction for classification of hyperspectral images using limited training samples", IEEE Geoscience and Remote Sensing Letters, Vol. 11, No. 8, (2014), 1325-1329. DOI: 10.1109/LGRS.2013.2292892
24.   Ahmad, M., Haq, D. I. U., Mushtaq, Q., & Sohaib, M. "A new statistical approach for band clustering and band selection using K-means clustering", IACSIT International Journal of Engineering and Technology, Vol. 3, No.6, (2011), 606-614.
25.   Sohaib, M., Ihsan-Ul-Haq and Q. Mushtaq, "Dimensional Reduction of Hyperspectral Image DataUsing Band Clustering and Selection Based on Statistical Characteristics of Band Images", International Journal of Computer and Communication Engineering, Vol. 2, No. 2, (2013), 101. http://www.ijcce.org/papers/148-B091.pdf
26.   Datta, A., S. Ghosh, and A. Ghosh, "Combination of clustering and ranking techniques for unsupervised band selection of hyperspectral images", IEEE Journal ofSelected Topics in Applied Earth Observations and Remote Sensing, Vol. 8, No. 6, (2015), 2814-2823. DOI: 10.1109/JSTARS.2015.2428276
27.   I ul Haq, I. and X. Xu. "A new approach to band clustering and selection for hyperspectral imagery". IEEE 9th International Conference on Signal Processing (ICSP), (2008). DOI: 10.1109/ICOSP.2008.4697345
28.   Saqui, D., Saito, J. H., Campos, J. R., & Jorge, L. A. D. C. "Approach Based on Fuzzy C-Means for Band Selection in Hyperspectral Images",International Journal of Computer, Electrical, Automation, Control and Information Engineering, Vol. 10, No.5, (2016), 889-895.https://publications.waset.org/10004410/approach-based-on-fuzzy-c-means-for-band-selection-in-hyperspectral-images
29.   Naik, G.R., Advances in Principal Component Analysis: Research and Development. 2017, Springer. Hardcover ISBN 978-981-10-6703-7. DOI:10.1007/978-981-10-6704-4
30.   MacQueen, J. "Some methods for classification and analysis of multivariate observations". In Proceedings of the fifth Berkeley symposium on mathematical statistics and probability. (1967). Oakland, CA, USA.
31.   Richards, J.A. and J. Richards, Remote sensing digital image analysis. Vol. 3. 1999: Springer. Hardcover ISBN 978-3-642-30061-5. DOI :10.1007/978-3-642-30062-2
32.   Beirami, B.A. and Mokhtarzade, M, "SVM classification of hyperspectral images using the combination of spectral bands and Moran's I features". IEEE 10th Iranian Conference on Machine Vision and Image Processing (MVIP), (2017). DOI: 10.1109/IranianMVIP.2017.8342334
33.   Beirami, Behnam Asghari, and Mehdi Mokhtarzade. "Band Grouping SuperPCA for Feature Extraction and Extended Morphological Profile Production from Hyperspectral Images." IEEE Geoscience and Remote Sensing Letters, Vol. 17, No. 11, (2020), 1953-1957. DOI: 10.1109/LGRS.2019.2958833
34.   Beirami, Behnam Asghari, and Mehdi Mokhtarzade. "Superpixel-Based Minimum Noise Fraction Feature Extraction for Classification of Hyperspectral Images." Traitement du Signal, Vol. 37, No. 5, (2020). DOI: https: //doi.org/10.18280/ts.370514