Abstract:A novel method was developed to classify hyperspectral remote sensing image based on independent component analysis (ICA) and support vector machine (SVM) algorithms. The characteristic information of the hyperspectral remote sensing image captured by PHI (made in China, with 80 bands) was extracted by ICA algorithm, and SVM classifier was established with the extracted image data (20 spectral dimensions). After kernel function selecting and parameter optimizing, it was found that the SVM algorithm(RBF kernel function; parameter C=103, γ=0.05)with accuracy 94.512 7% and kappa coefficient 0.935 1 has the best classification result, better than the results of four kinds of conventional algorithms, including neural net classification (accuracy 39.475 8% and kappa coefficient 0.315 5), spectral angle mapper classification (accuracy 80.282 6% and kappa coefficient 0.770 9), minimum distance classification (accuracy 85.462 7% and kappa coefficient 0.827 7) and maximum likelihood classification (accuracy 86.015 6% and Kappa coefficient 0.835 1). In order to control the “pepper and salt” phenomenon which appeared in classification map frequently, the classification result of SVM (RBF kernel) was operated by the method of clump classes using the morphological operators, and that the classification map closer to actual situation was acquired, with the accuracy and kappa coefficient increasing to 94.758 4% and 0.938 0, respectively. The study indicated that the ICA combined with SVM was an preferred method for hyperspectral remote sensing image classification, and clump classes was a effective method to optimized the classification result.
[1] TONG Qing-xi, ZHANG Bing, ZHENG Lan-fen(童庆禧, 张 兵, 郑兰芬). Hyperspectral Remote Sensing—Theory, Technology and Application(高光谱遥感—原理、技术与应用). Beijing: Higher Education Press(北京: 高等教育出版社), 2006. [2] PU Rui-liang, GONG Peng(浦瑞良, 宫 鹏). Hyperspectral Remote Sensing and Its Applications(高光谱遥感及其应用). Beijing: Higher Education Press(北京: 高等教育出版社), 2000. [3] ZHANG Liang-pei, ZHANG Li-fu(张良培, 张立福). Hyperspectral Remote Sensing(高光谱遥感). Wuhan: Wuhan University Press(武汉: 武汉大学出版社), 2005. [4] WAN Yu-qing, TAN Ke-long, ZHOU Ri-ping(万余庆, 谭克龙, 周日平). Application of Hyperspectral Remote Sensing(高光谱遥感应用研究). Beijing: Science Press(北京: 科学出版社), 2006. [5] LIANG Liang, LIU Zhi-xiao, YANG Min-hua, et al(梁 亮, 刘志霄, 杨敏华, 等). Journal of Infrared and Millimeter Waves(红外与毫米波学报), 2009, 28(5): 353. [6] WU Di, HE Yong, FENG Shui-juan, et al(吴 迪, 何 勇, 冯水娟, 等). Journal of Infrared and Millimeter Waves红外与毫米波学报), 2008, 27(3): 180. [7] WANG Li-guo,ZHAO Chun-hui,QIAO Yu-long, et al(王立国, 赵春晖, 乔玉龙, 等). Journal of Infrared and Millimeter Waves(红外与毫米波学报), 2008, 27(6): 442. [8] Sun D Y, Li Y M, Wang Q A. IEEE Transaction on Geoscience and Remote Sensing, 2009, 47(8): 2957. [9] SU Ling-hua, YI Tong-sheng, WAN Jian-wei(苏令华, 衣同胜, 万建伟). Acta Photonica Sinica(光子学报), 2008, 37(5): 973. [10] Tu T M, Huang P S, Chen P Y. IEEE Proceedings on Vision, Image and Signal Processing, 2001, 148(4): 217. [11] WANG J, CHANG C I. IEEE Transactions on Geoscience and Remote Sensing, 2006, 44(6): 1586. [12] Lee T W. Independent Component Analysis: Theory and Applications. Boston: Kluwer Academic Publisher, 1998. [13] Hyvarinen A, Oja E. Neural Networks, 2000, 12(4-5): 411. [14] Hyvarinen A. IEEE Transactions on Neural Networks, 1999, 10(3): 626. [15] Vapnik V N. Statistical Learning Theory. New York: Wiley, 1998. [16] John Shawe-Taylor, Nello Cristianini. Kernel Methods for Pattern Analysis. Cambridge University Press, 2004. [17] HSU Chih-wei, CHANG Chih-chung, LIN Chih-jen. http://ntu.csie.org/~cjlin/papers/guide/guide.pdf.