Hyperspectral Image Classification Based on 3-D Gabor Filter and Support Vector Machines
FENG Xiao1, 2, XIAO Peng-feng2*, LI Qi1, LIU Xiao-xi2, WU Xiao-cui2
1. Institute of Remote Sensing and GIS, Peking University, Beijing 100871, China 2. Department of Geographical Information Science, Nanjing University, Nanjing 210023, China
Abstract:A three-dimensional Gabor filter was developed for classification of hyperspectral remote sensing image. This method is based on the characteristics of hyperspectral image and the principle of texture extraction with 2-D Gabor filters. Three-dimensional Gabor filter is able to filter all the bands of hyperspectral image simultaneously, capturing the specific responses in different scales, orientations, and spectral-dependent properties from enormous image information, which greatly reduces the time consumption in hyperspectral image texture extraction, and solve the overlay difficulties of filtered spectrums. Using the designed three-dimensional Gabor filters in different scales and orientations, Hyperion image which covers the typical area of Qi Lian Mountain was processed with full bands to get 26 Gabor texture features and the spatial differences of Gabor feature textures corresponding to each land types were analyzed. On the basis of automatic subspace separation, the dimensions of the hyperspectral image were reduced by band index (BI) method which provides different band combinations for classification in order to search for the optimal magnitude of dimension reduction. Adding three-dimensional Gabor texture features successively according to its discrimination to the given land types, supervised classification was carried out with the classifier support vector machines (SVM). It is shown that the method using three-dimensional Gabor texture features and BI band selection based on automatic subspace separation for hyperspectral image classification can not only reduce dimensions, but also improve the classification accuracy and efficiency of hyperspectral image.
[1] TONG Qing-xi, ZHANG Bing, ZHENG Lan-fen(童庆禧, 张 兵, 郑兰芬). Hyperspectral Remote Sensing(高光谱遥感). Beijing: Higher Education Press(北京: 高等教育出版社), 2006. [2] Du Q, Yang H. IEEE Geoscience and Remote Sensing Letters, 2008, 5(4): 564. [3] Martinez-Uso A, Pla F, Sotoca J M, et al. IEEE Transactions on Geoscience and Remote Sensing, 2007, 45(12): 4158. [4] Gu Y F, Zhang Y. Proceedings of International Conference on Image Processing, 2003, 1: 801. [5] Sarkar S, Healey G. Optical Engineering, 2004, 43(12): 3038. [6] Chen M, Strobl J. International Journal of Remote Sensing, 2013, 34(13): 4550. [7] Shi M, Healey G. IEEE Transactions on Geoscience and Remote Sensing, 2005, 43(5): 1201. [8] Hauta-Kasari M, Parkkinen J, Jaaskelainen T, et al. Proceedings of the 13th International Conference on Pattern Recognition, 1996, 2(3): 785. [9] Licciardi G, Pacifici F, Tuia D, et al. IEEE Transactions on Geoscience and Remote Sensing, 2009, 47(11): 3857. [10] Daugman J G. Journal of the Optical Society of America A, 1985, 2(7): 1160. [11] Liu L, Ngadi M O, Prasher S O, et al. Journal of Food Engineering, 2010, 99(3): 284. [12] Li M, Staunton R C. Pattern Recognition Letters, 2008, 29(5): 664. [13] Xie X H. Electronic Letters on Computer Vision and Image Analysis, 2008, 7(3): 1. [14] Shen L L, Bai L. Medical Image Analysis, 2008, 12(3): 375. [15] Bau T C, Healey G. Proccedings of SPIE-Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XV, 2009, 73340B. [16] Bau T C, Sarkar S, Healey G. IEEE Transactions on Geoscience and Remote Sensing, 2010, 48(9): 3457. [17] Pal M, Foody G M. IEEE Transactions on Geoscience and Remote Sensing, 2010, 48(5): 2297. [18] Shashahani B M, Landgrebe D A. IEEE Transactions on Geoscience and Remote Sensing, 1994, 32(5): 1087.