Classification of Hyperspectral Images Using Cluster Space Linear Discriminant Analysis and Small Training Set
Subject Areas : electrical and computer engineering
M.
Imani
1
(Tarbiat Modares University)
H.
Ghassemian
2
(Tarbiat Modares University)
Keywords: Classification clustering feature extraction hyperspectral training sample,
Abstract :
The hyperspectral images allow us to discriminate between different classes with more details. There are lots of spectral bands in hyperspectral images. On the other hand, the limited number of available training samples causes difficulties in classification of high dimensional data. Since the gathering of training samples is hard and time consuming, feature reduction can considerably improve the performance of classification. So, feature extraction is one of the most important preprocessing steps in analysis and classification of hyperspectral images. Feature extraction methods such as LDA have not good efficiency in small sample size situation. A supervised feature extraction method is proposed in this paper. The proposed method, which is called cluster space linear discriminant analysis (CSLDA), without obtaining the label of testing samples and just with doing a clustering on testing data, finds the relationship between training and testing samples. Then, it uses the power of unlabeled samples together with training samples for estimation of within-class and between-class scatter matrices. The CSLDA improves the classification accuracy particularly in multimodal hyperspectral data. The experimental results on urban and agriculture hyperspectral images show the better performance of CSLDA compared to popular feature extraction methods such as LDA, GDA, and NWFE using limited number of training samples.
[1] G. F. Hughes, "On the mean accuracy of statistical pattern recognition," IEEE Trans. Inf. Theory, vol. 14, no. 1, pp. 55-63, Jan. 1968.
[2] G. Moser and S. B. Serpico, "Combining support vector machines and markov random fields in an integrated framework for contextual image classification," IEEE Trans. on Geoscience and Remote Sensing, vol. 51, no. 5, pp. 2734-2752, May 2013.
[3] B. Demir and S. Erturk, "Clustering-based extraction of border training patterns for accurate SVM classification of hyperspectral images," IEEE Geoscience and Remote Sensing Lett., vol. 6, no. 4, pp. 840-844, Oct. 2009.
[4] M. Imani and H. Ghassemian, "Adaptive expansion of training samples for improving hyperspectral image classification performance," in Proc. 21st Iranian Conf. on Electrical Engineering, 6 pp., May 2013.
[5] X. Jia, B. C. Kuo, and M. Crawford, "Feature mining for hyperspectral image classification," Proceedings of the IEEE, vol. 101, no. 3, pp. 676-697, Mar. 2013.
[6] M. Kamandar and H. Ghassemian, "Linear feature extraction for hyperspectral images based on information theoretic learning," IEEE Geoscience and Remote Sensing Lett., vol. 10, no. 4, pp. 702-706, Jun. 2013.
[7] M. Imani and H. Ghassemian, "Band clustering-based feature extraction for classification of hyperspectral images using limited training samples," IEEE Geoscience and Remote Sensing Lett., vol. 11, no. 8, pp. 1325-1329, Aug. 2014.
[8] D. Korycinski, M. Crawford, J. W. Barnes, and J. Ghosh, "Adaptive feature selection for hyperspectral data analysis using a binary hierarchical classifier and tabu search," in Proc. IEEE Symp. on Geoscience and Remote Sensing, vol. 1, pp. 297-299, Jul. 2003S. [9] S. Li, H. Wu, D. Wan, and J. Zhu, "An effective feature selection method for hyperspectral image classification based on genetic algorithm and support vector machine," Knowledge-Based Systems, vol. 24, no. 1, pp. 40-48, Feb. 2011.
[10] K. Fukunaga, Introduction to Statistical Pattern Recognition, San Diego: Academic Press Inc., 1990.
[11] G. Baudat and F. Anouar, "Generalized discriminant analysis using a kernel approach," Neural Comput., vol. 12, no. 10, pp. 2385-2404, Oct. 2000.
[12] B. C. Kuo and D. A. Landgrebe, "Nonparametric weighted feature extraction for classification," IEEE Trans. Geosci. Remote Sens, vol. 42, no. 5, pp. 1096-1105, May 2004.
[13] X. F. He and P. Niyogi, "Locality preserving projections," in Proc. Adv. Neural Inf. Process. Syst., vol. 16, pp. 153-160, 2004.
[14] X. F. He, D. Cai, S. C. Yan, and H. J. Zhang, "Neighborhood preserving embedding," in Proc. 10th IEEE Int. Conf. Comput. Vis., ICCV'05, vol. 2, pp. 1208-1213, 17-21 Oct. 2005.
[15] H. Y. Huang and B. C. Kuo, "Double nearest proportion feature extraction for hyperspectral-image classification," IEEE Trans. Geosci. Remote Sens., vol. 48, no. 11, pp. 4034-4046, Nov. 2010.
[16] J. Wen, Z. Tian, X. Liu, and W. Lin, "Neighborhood preserving orthogonal PNMF feature extraction for hyperspectral image classification," IEEE J. of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 6, no. 2, pp. 759-768, Apr. 2013.
[17] A. M. MartoAnez and A. C. Kak, "PCA versus LDA," IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 23, no. 2, pp. 228-233, Feb. 2001.
[18] J. H. Friedman, "Regularized discriminant analysis," J. of the American Statistical Association, vol. 84, no. 405, pp. 165-175, Mar. 1989.
[19] C. Chang and C. Linin, LIBSVM-A Library for Support Vector Machines, 2008. [Online], Available: http://www.csie.ntu.edu.tw/~cjlin/libsvm.
[20] J. Cohen, "A coefficient of agreement from nominal scales," Edu. Psychol. Meas., vol. 20, no. 1, pp. 37-46, Apr. 1960.
[21] G. M. Foody, "Thematic map comparison: evaluating the statistical significance of differences in classification accuracy," Photogramm. Eng. Remote Sens., vol. 70, no. 5, pp. 627-633, May 2004.