High performance of the support vector machine in classifying hyperspectral data using a limited dataset

Document Type : Research Paper


1 Faculty of Mining, Petroleum and Geophysics, Shahrood University of Technology, Shahrood, Iran

2 Department of Ecology, Institute of Science and High Technology and Environmental Science, Graduate University of Advanced Technology, Kerman, Iran.

3 Faculty of Computer Engineering, Zanjan University, Zanjan, Iran

4 Mining Engineering Group, Faculty of Engineering, Zanjan University, Zanjan, Iran


To prospect mineral deposits at regional scale, recognition and classification of hydrothermal alteration zones using remote sensing data is a popular strategy. Due to the large number of spectral bands, classification of the hyperspectral data may be negatively affected by the Hughes phenomenon. A practical way to handle the Hughes problem is preparing a lot of training samples until the size of the training set is adequate and comparable with the number of the spectral bands. In order to gather adequate ground truth instances as training samples, a time-consuming and costly ground survey operation is needed. In this situation that preparing enough field samples is not an easy task, using an appropriate classifier which can properly work with a limited training dataset is highly desirable. Among the supervised classification methods, the Support Vector Machine is known as a promising classifier that can produce acceptable results even with limited training data. Here, this capability is evaluated when the SVM is used to classify the alteration zones of Darrehzar district. For this purpose, only 12 sampled instances from the study area are utilized to classify Hyperion hyperspectral data with 165 useable spectral bands. Results demonstrate that if parameters of the SVM, namely C and σ, are accurately adjusted, the SVM can be successfully used to identify alteration zones when field data samples are not available enough.


[1] Alajlan, N., Bazi, Y., Melgani, F., Yager, R. (2012). Fusion of supervised and unsupervised learning for improved classification of hyperspectral images. Journal of Information Sciences 217, 39-55. Doi: 10.1016/j.ins.2012.06.031
[2] Amer, R., Kusky, T., El Mezayen, A. (2012). Remote sensing detection of gold related alteration zones of Um Rus Area, Central Eastern Desert of Egypt. Advances in Space Research, 49(1), 121-134. Doi:10.1016/j.asr.2011.09.024
[3] Bazi, Y. and Melgani, F. (2006). Toward an optimal SVM classification for hyperspectral remote sensing images. IEEE Transactions on Geoscience and Remote Sensing, 44(11), 3374-3385. Doi: 10.1109/TGRS.2006.880628
[4] Bishop, C.A., Liu, J.G., Mason, P.J. (2011). Hyperspectral remote sensing for mineral exploration in Pulang, Yunnan Province, China. International Journal of Remote Sensing, 32(7), 2409-2426. Doi: 10.1080/01431161003698336
[5] Camps-Valls, G., Gomez-Chova, L., Calpe-Maravilla, J., Martin-Guerrero, J.D., Soria-Olivas, E., Alonso-Chorda, L., Moreno, J. (2004). Robust support vector method for hyperspectral data classification and knowledge discovery. IEEE Transactions on Geoscience and Remote Sensing, 42, 1530-1542. Doi: 10.1109/TGRS.2004.827262
[6] Camps-Valls, G., Tuia, D., Bruzzone, L., Benediktsson, J. (2014). Advances in Hyperspectral Image Classification. IEEE Signal Processing Magazine, 31(1), 45-54. Doi: 10.1109/MSP.2013.2279179
[7] Chang, C. (2007). Hyperspectral Data Exploitation, Theory and Applications. Published by John Wiley & Sons, Inc., Hoboken, New Jersey.
[8] Cortes, C. and Vapnik, V. (1995). Support-vector Networks. Machine Learning, 20(3), 273-297.
[9] Duda, R.O., Hart, P. E., Stork, D. G., (1973). Pattern Classification. Published by Wiley-Interscience ©2000, 2nd Edition.
[10] Fauvel, M., Tarabalka, Y., Benediktsson, J.A., Chanussot, J., Tilton, J.C. (2013). Advances in Spectral-Spatial Classification of Hyperspectral Images. Proceedings of the IEEE, 101(3), 652-675. Doi: 10.1109/JPROC.2012.2197589
[11] Foody, G.M. and Mathur, A. (2004b). Toward intelligent training of supervised image classifications: directing training data acquisition for SVM classification. Remote Sensing of Environment, 93(1-2): 107-117. Doi: 10.1016/j.rse.2004.06.017
[12] Geological survey of Iran. (1973a). Exploration for Ore deposits in Kerman region. Report No, Yu/53. Tehran, Iran: Ministry of Economy Geological Survey of Iran.
[13] Gersman, R., Ben-Dor, E., Beyth, M., Avigad, D., Abraha, M., Kibreba, A. (2008). Mapping of hydrothermal altered rocks by the EO-1 Hyperion sensor, northern Danakil, Eritrea. International Journal of Remote Sensing, 29(13), 3911-3936. Doi: 10.1080/01431160701874587
[14] Gheyas, A., Leslie, S.S. (2010). Feature subset selection in large dimensionality domains, Pattern Recognition, 43, 5-13. Doi: 10.1016/j.patcog.2009.06.009
[15] Heikkila, J.(1992). ESTIMATION OF CLASSIFIER'S PERFORMANCE WITH ERROR COUNTING, XVIIth ISPRS Congress, Technical Commission III: Mathematical Analysis of Data, Washington, D.C., USA, August 2-14,325-334.
[16] Hosseinjani Zadeh, M., Tangestani, M.H. (2011). Mapping alteration minerals using sub-pixel unmixing of ASTER data in the Sarduiyeh area, southeastern Kerman Iran. International Journal of Digital Earth, 4(6), 487-504. Doi: 10.1080/17538947.2010.550937
[17] Hosseinjani Zadeh, M., Tangestani, M.H., Velasco Roldan, F., Yusta, I. (2014a). Sub-pixel mineral mapping of a porphyry copper belt using EO-1 Hyperion data. Advances in Space Research, 53(3), 440-451. Doi: 10.1016/j.asr.2013.11.029
[18] Hosseinjani Zadeh, M., Tangestani, M.H., Velasco Roldan, F., Yusta, I. (2014b). Mineral exploration and alteration zone mapping using mixture tuned matched filtering approach on ASTER data at the central part of Dehaj-Sarduiyeh copper belt, SE Iran. IEEE selected topics in applied earth observations and remote sensing. 7(1),284-289.Doi: 10.1109/JSTARS.2013.2261800
[19] Huang, C., Song, K., Kim, S., Townshend, J.R.G., Davis, P., Masek, J.G., Goward, S.N. (2008). Use of dark object concept and support vector machines to automate forest cover change analysis. Remote Sensing of Environment, 112(3), 970-985. Doi: 10.1016/j.rse.2007.07.023
[20] Kruse, F.A. (2003). Mineral Mapping with AVIRIS and EO-1 Hyperion. Presented at the 12th JPL Airborne Geoscience Workshop, Pasadena, California.
[21] Kruse, JW. and Boardman, F.A. (2000). Characterization and Mapping of Kimberlites and Related Diatremes Using Hyperspectral Remote Sensing. IEEE Aerospace Conference Proceedings, 3, 18-24. Doi: 10.1109/AERO.2000.879859
[22] Kruse, F.A., Boardman, J.W., Huntigton, J.F. (2003). Comparison of airborne Hyperspectral data and EO-1 Hyperion for mineral mapping. IEEE Transactions on Geoscience and Remote Sensing, 41(6), 1388-1400. Doi: 10.1109/TGRS.2003.812908
[23] Landgrebe, D.A. (2002). Hyperspectral Image Data Analysis. IEEE Signal processing Magazine, 19(1), 17-28. Doi: 10.1109/79.974718
[24] Li, J. and Bioucas-Dias, J.M. (2013). Semi-supervised Hyperspectral Image Classification Using Soft Sparse Multinomial Logistic Regression. Geoscience and Remote Sensing Letters, IEEE, 10(2), 318-322. Doi: 10.1109/LGRS.2012.2205216
[25] Martin, G. K., Hirschberg, D. S. (1996). Small Sample Statistics for Classification Error Rates. Technical report, No, 96-21. Department of Information and Computer Science, University of California.
[26] Mountrakis, G., Im, J., Ogole, C. (2011). Support vector machines in remote sensing: A review. ISPRS Journal of Photogrammetry and Remote Sensing, 66, 247-259. Doi:10.1016/j.isprsjprs.2010.11.001
[27] NICICO. (2008). Darrehzar ore reserve estimates. Internal report of National Iranian Copper Industries Company.
[28] Okujeni, A., van der Linden, S., Tits, L., Somers, B., Hostert P. (2013). Support vector regression and synthetically mixed training data for quantifying urban land cover. Remote Sensing of Environment, 137, 184-197. Doi: 10.1016/j.rse.2013.06.007
[29] Oommen, T. (2008). An objective analysis of Support Vector Machine based classification for remote sensing, Mathematical Geosciences, 40(4), 409-424. Doi: 10.1007/s11004-008-9156-6
[30] Pal, M. and Foody, G.M. (2010). Feature Selection for Classification of Hyperspectral Data by SVM. IEEE Transactions on Geoscience and Remote Sensing, 48(5), 2297-2307. Doi: 10.1109/TGRS.2009.2039484
[31] Pal, M. and Mather, P.M. (2005). Support vector machines for classification in remote sensing. International Journal of Remote Sensing, 26(5), 1007-1011. Doi: 10.1080/01431160512331314083
[32] Petropoulos, G.P., Kontoes, C., Keramitsoglou, I. (2011). Burnt Area Delineation from a uni-temporal perspective based on Landsat TM imagery classification using Support Vector Machines. International Journal of Applied Earth Observation and Geoinformation, 13(1), 70-80. Doi: 10.1016/j.jag.2010.06.008
[33] Plaza, A., Benediktsson, J.A., Boardman, J.W., Brazile, J., Bruzzone, L., Camps-Valls, G., Chanussot, J., Fauvel, M., Gamba, P., Gualtieri, A., Marconcini, M., Tilton, J.C., Trianni, G. (2009). Recent advances in techniques for hyperspectral image processing. Remote Sensing of Environment, 113, 110-122. Doi: 10.1016/j.rse.2007.07.028
[34] Ranjbar, H., Hassanzadeh, H.,Torabi, M. (2001). Integration and analysis of airborne geophysical data of the Darrehzar area, Kerman Province, Iran, using principal component analysis. Journal of Applied Geophysics, 48(1), 33-41, Doi: 10.1016/S0926-9851(01)00059-3
[35] Shahriari, H., Honarmand, M., Ranjbar, H. (2015). Comparison of multi-temporal ASTER images for hydrothermal alteration mapping using a fractal-aided SAM method. International Journal of Remote Sensing, 36(5), 1271–1289. Doi: 10.1080/01431161.2015.1011352
[36] Shahriari, H; Ranjbar, H; Honarmand, M. (2013). Image Segmentation for Hydrothermal Alteration Mapping Using PCA and Concentration–Area Fractal Model. Natural Resources Research, 22(3), 191-206, Doi: 10.1007/s11053-013-9211-y
[37] Wang, Z.H. and Zheng, C.Y. (2010). Rocks/Minerals Information Extraction from EO-1 Hyperion Data Base on SVM. International Conference on Intelligent Computation Technology and Automation, 3, 229-232. Doi: 10.1109/ICICTA.2010.341
[38] Waske, B., Benediktsson, J.A., Arnason, K., Sveinsson, J.R. (2009). Mapping of hyperspectral AVIRIS data using machine-learning algorithms. Canadian Journal of Remote Sensing, 35(1), 106-116.
[39] Waterman, G. and Hamilton, N. (1975). The Sarcheshmeh porphyry copper deposit. Economic Geology, 70, 568-576
[40] Yanfeng, G.u., Wang, S., Xiuping, J. (2013). Spectral Unmixing in Multiple-Kernel Hilbert Space for Hyperspectral Imagery. IEEE Transactions on Geoscience and Remote Sensing, 51(7), 3968-3981. Doi: 10.1109/TGRS.2012.2227757
[41] Zhang, X. and Peijun, L. (2014). Lithological mapping from hyperspectral data by improved use of spectral angle mapper. International Journal of Applied Earth Observation and Geoinformation, 31, 95-109. Doi: 10.1016/j.jag.2014.03.007
[42] Zollanvari, A., Braga-Neto, U.M, Dougherty, E.R. (2010). Joint Sampling Distribution Between Actual and Estimated Classification Errors for Linear Discriminant Analysis. IEEE Transactions on INFORMATION THEORY, 56(2).Doi: 10.1109/TIT.2009.2037034