Abstract：In order to reduce the redundancy between hyperspectral band images, decrease the computing time and facilitate the following classification task, a hyperspectral band selection algorithm based on kernelized fuzzy rough set was proposed. Due to strong similarity between adjacent bands of hyperspectral images, the kernelized fuzzy rough set theory was introduced to measure the importance of bands more effectively. Considering the distribution characteristics of categories in the bands, the correlation between bands was defined according to the distribution of the lower approximate set of bands, and then the importance of bands was defined by combining the information entropy of bands. The search strategy of maximum correlation and maximum importance was used to realize the band selection of hyperspectral images. Finally, experiments were conducted on the commonly used hyperspectral dataset Indiana Pines agricultural area by using the J48 and KNN classifiers. Compared with other hyperspectral band selection algorithms, this algorithm has overall average classification accuracy increased by 4.5 and 6.6 percentage points respectively with two classifiers. The experimental results show that the proposed algorithm has some advantages in hyperspectral band selection.
[1] HUGHES G. On the mean accuracy of statistical pattern recognizers[J]. IEEE Transactions on Information Theory, 1968, 14(1):55-63. [2] AGARWAL A, EL-GHAZAWI T, EL-ASKARY H, et al. Efficient hierarchical-PCA dimension reduction for hyperspectral imagery[C]//Proceedings of the 2007 IEEE International Symposium on Signal Processing and Information Technology. Piscataway:IEEE, 2007:353-356. [3] LI W, PRASAD S, FOWLER J E, et al. Locality-preserving dimensionality reduction and classification for hyperspectral image analysis[J]. IEEE Transactions on Geoscience and Remote Sensing, 2012, 50(4):1185-1198. [4] WANG J, CHANG C I. Independent component analysis-based dimensionality reduction with applications in hyperspectral image analysis[J]. IEEE Transactions on Geoscience and Remote Sensing, 2006, 44(6):1586-1600. [5] LIU Y, YANG J, CHEN Y, et al. Stability analysis of hyperspectral band selection algorithms based on neighborhood rough set theory for classification[J]. Chemometrics and Intelligent Laboratory Systems, 2017, 169:35-44. [6] PATRA S, MODI P, BRUZZONE L. Hyperspectral band selection based on rough set[J]. IEEE Transactions on Geoscience and Remote Sensing, 2015, 53(10):5495-5503. [7] GUO B, GUNN S R, DAMPER R I, et al. Band selection for hyperspectral image classification using mutual information[J]. IEEE Geoscience and Remote Sensing Letters 2006, 3:522-526. [8] 刘春红,赵春晖,张凌雁. 一种新的高光谱遥感图像降维方法[J]. 中国图象图形学报, 2005, 10(2):218-222. (LIU C H, ZHAO C H, ZHANG L Y. A new method of hyperspectral remote sensing image dimensional reduction[J]. Journal of Image and Graphics, 2005, 10(2):218-222.) [9] 刘雪松,葛亮,王斌,等. 基于最大信息量的高光谱遥感图像无监督波段选择方法[J]. 红外与毫米波学报, 2012, 31(2):166-170, 176. (LIU X S, GE L, WANG B, et al. An unsupervised band selection algorithm for hyperspectral imagery based on maximal information[J]. Journal of Infrared and Millimeter Waves, 2012, 31(2):166-170, 176.) [10] 葛亮,王斌,张立明. 基于波段聚类的高光谱图像波段选择[J]. 计算机辅助设计与图形学学报, 2012, 24(11):1447-1454. (GE L, WANG B, ZHANG L M. Band selection of hyperspectral images based on band clustering[J]. Journal of Computer-Aided Design and Graphics, 2012, 24(11):1447-1454.) [11] MARTINEZ-USO A, PLA F, SOTOCA J M. Clustering-based hyperspectral band selection using information measures[J]. IEEE Transactions on Geoscience and Remote Sensing, 2007, 45(12):4158-4171. [12] 陈水利. 模糊集理论及其应用[M]. 北京:科学出版社, 2005:73-82. (CHEN S L. Fuzzy Set Theory and Application[M]. Beijing:Science Press, 2005:73-82.) [13] DUBOIS D, PRADE H. Rough fuzzy sets and fuzzy rough sets[J]. International Journal of General System, 1990, 17(2/3):191-209. [14] HU Q, YU D, PEDRYCZ W, et al. Kernelized fuzzy rough sets and their applications[J]. IEEE Transactions on Knowledge and Data Engineering, 2010, 23(11):1649-1667. [15] CORTES C, VAPNIK V. Support-vector networks[J]. Machine Learning, 1995, 20(3):273-297. [16] MOSER B. On representing and generating kernels by fuzzy equivalence relations[J]. Journal of Machine Learning Research, 2006, 7:2603-2620. [17] HU Q, ZHANG L, CHEN D, et al. Gaussian kernel based fuzzy rough sets:model, uncertainty measures and applications[J]. International Journal of Approximate Reasoning, 2010, 51(4):453-471. [18] ZHANG W, LI X, ZHAO L. A fast hyperspectral feature selection method based on band correlation analysis[J]. IEEE Geoscience and Remote Sensing Letters, 2018, 15(11):1750-1754.
2020, Vol. 40 
