Sparse Spatio-Spectral LapSVM with Semisupervised Kernel Propagation for Hyperspectral Image Classification

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

Volumn 10, Issue 5, 2017, Pages 2046-2054

  Yang, Lixia ^a,b   Wang, Min ^a   Yang, Shuyuan ^c   Zhang, Rui ^a   Zhang, Pingting ^a  

^a XIDIAN UNIVERSITY   (China)

^b NINGXIA UNIVERSITY   (China)

^c Department of Electrical Engineering   (China)

Author keywords

Hyperspectral image classification (HIC); semisupervised kernel propagation (KP); sparse pruning

Indexed keywords

CLASSIFICATION (OF INFORMATION); HYBRID INTEGRATED CIRCUITS; SPECTROSCOPY;

COMPUTATION COSTS; HYPERSPECTRAL DATA; KERNEL MATRICES; PRUNING ALGORITHMS; REGULARIZATION TERMS; SPATIAL REGULARIZATIONS; SPECTRAL INFORMATION; UNLABELED SAMPLES;

IMAGE CLASSIFICATION;

ACCURACY ASSESSMENT; EFFICIENCY MEASUREMENT; IMAGE CLASSIFICATION; PIXEL; SPECTRAL ANALYSIS; SUPPORT VECTOR MACHINE; TOPOLOGY;

EID: 85016127121     PISSN: 19391404     EISSN: 21511535     Source Type: Journal    
DOI: 10.1109/JSTARS.2016.2647640     Document Type: Article

References (38)

1. F. Melgani and L. Bruzzone, "Classification of hyperspectral remote sensingimages with support vector machines, " IEEE Trans. Geosci. RemoteSens., vol. 42, no. 8, pp. 1778-1790, Aug. 2004.
2. P. Ramzi, F. Samadzadegan., P. Reinartz, "Classification of hyperspectraldata using an AdaBoostSVM technique applied on band clusters, "IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens., vol. 7, no. 6, pp. 2066-2079, Jun. 2014.
3. P. Zhong and R. S. Wang, "Learning conditional random fields for classificationof hyperspectral images, " IEEE Trans. Image Process., vol. 19, no. 7, pp. 1890-1907, Jul. 2015.
4. S. J. Sun, P. Zhong, H. T. Xiao., R. S. Wang, "Active learning withGaussian process classifier for hyperspectral image classification, " IEEETrans. Geosci. Remote Sens., vol. 53, no. 4, pp. 1745-1760, Apr. 2015.
5. J. Li, J. M. B. Dias., A. Plaza. Semi-supervised hyperspectral imageclassification using soft sparse multinomial logistic regression. IEEEGeosci. Remote Sens. Lett., vol. 10, no. 2, pp. 318-322, 2013.
6. Z. Sun, C. Wang, D. L. Li., J. Li, "Semisupervised classification forhyperspectral imagery with transductive multiple-kernel learning, " IEEEGeosci. Remote Sens. Lett., vol. 11, no. 11, pp. 1991-1995, Nov. 2014.
7. C. V. Gustavo, V. B. M. Tatyana., D. Y. Zhou, "Semi-supervised graphbasedhyperspectral image classification, " IEEE Trans. Geosci. RemoteSens., vol. 45, no. 10, pp. 3044-3054, Oct. 2007.
8. G. Camps-Valls, L. Gomez-Chova, J. Munoz-Mari, J. Vila-Frances., J. Calpe-Maravilla, "Composite kernels for hyperspectral image classification, "IEEE Geosci. Remote Sens. Lett., vol. 3, no. 1, pp. 1-5, Jan. 2006.
9. S. Y. Yang, Y. Qiao, L. Yang, P. Jin., L. Jiao, "Hyperspectral imageclassification based on relaxed clustering assumption and spatialLaplace regularizer, " IEEE Geosci. Remote Sens. Lett., vol. 11, no. 5, pp. 901-9055, May 2014.
10. Y. C. Zhou, J. T. Peng., C. L. P. Chen, "Extreme learning machine withcomposite kernels for hyperspectral image classification, " IEEE J. Select. Topics Appl. Earth Observ. Remote Sens., vol. 8, no. 6, pp. 2351-2360, Jun. 2015.
11. B. B. Damodaran, R. R. Nidamanuri., Y. Tarabalka, "Dynamic ensembleselection approach for hyperspectral image classification withjoint spectral and spatial information, " IEEE J. Sel. Topics Appl. EarthObserv. Remote Sens., vol. 8, no. 6, pp. 2405-2417, Jun. 2015.
12. L. X. Yang, S. Y. Yang, P. L. Jin., R. Zhang, "Semi-supervised hyperspectralimage classification using spatio-spectral Laplacian support vectormachine, "IEEE Geosci. Remote Sens. Lett., vol. 11, no. 3, pp. 651-655, Mar. 2014.
13. L. G. Wang, S. Y. Hao, Q. M. Wang., Y. Wang, "Semi-supervisedclassification for hyperspectral imagery based on spatial-spectral labelpropagation, " ISPRS J. Photogramm. Remote Sens., vol. 97, pp. 123-137, 2014.
14. L. G. Wang, Y. S. Yang., D. F. Liu, "Semisupervised classification forhyperspectral image based on spatial-spectral clustering, " J. Appl. RemoteSens., vol. 9, no. 1, 2015, Art. no. 096037.
15. L. Ma, A. D. Ma, C. Ju., X. M. Li, "Graph-based semi-supervisedlearning for spectral-spatial hyperspectral image classification, " PatternRecog. Lett., vol. 83, no. 2, pp. 133-142, Nov. 2016.
16. G. Camps-Valls, L. Gomez-Chova., J. Calpe-Maravilla, "Robustsupport vector method for hyperspectral data classification and knowledgediscovery, " IEEE Trans. Geosci. Remote Sens., vol. 42, no. 7, pp. 1530-1542, Jul. 2004.
17. C. H. Li et al., "An automatic method for selecting the parameter of thenormalized kernel function to support vector machines, " J. Inf. Sci. Eng., vol. 28, pp. 1-15, 2012.
18. P. J. Hsieh, C. H. Li., B. C. Kuo, "A nonlinear feature selection methodbased on kernel separability measure for hyperspectral image classification, "in Proc. 2015 IEEE Int. Geosci. Remote Sens. Symp., Milan, Italy, 2015, pp. 461-464.
19. X. Y. Zhang, D. Y. Qiu., F. A. Chen, "Support vector machinewith parameter optimization by a novel hybrid method and its applicationto fault diagnosis, " Neurocomputing, vol. 149, pp. 641-651, 2015.
20. J. Yang, H. Lee., N. Kwak, "Kernel parameter selection by gap maximizationbetween intra and inter-class samples, " in Proc. 2016 Int. Conf. Big Data and Smart Comput., Hong Kong, 2016, pp. 349-352.
21. L. Zhang, W. D. Zhou., L. C. Jiao, "Wavelet support vector machine, "IEEE Trans. Syst., Man, Cybern. B, Cybern., vol. 34, no. 1, pp. 34-39, Feb. 2004.
22. T. Hofmann, B. Schölkopf., A. J. Smola, "Kernel methods in machinelearning, " Ann. Statist., vol. 36, no. 3, pp. 1171-1220, 2008.
23. S. Boughorbel, J. P. Tarel., N. Boujemaa, "Conditionally positivedefinite kernels for SVM based image recognition, " In Proc. IEEE Int. Conf. Multimedia Expo., 2005, pp. 113-116.
24. S. Boughorbel, J. P. Tarel., N. Boujemaa, "Generalized histogramintersection kernel for image recognition, " In Proc. IEEE Int. Conf. ImageProcess., 2005, pp. 161-164.
25. V. A. Zimmer et al., "A framework for optimal kernel-based manifoldembedding of medical image data, " Comput. Med. Imag. Graph., vol. 41, pp. 93-107, 2015.
26. Z. H. Zhang, J. T. Kwok., D. Y. Yeung, "Model-based transductivelearning of the kernel matrix, " Mach. Learn., vol. 63, no. 1, pp. 69-101, Mar. 2006.
27. E. Hu, S. Chen, D. Zhang., X. Yin, "Semisupervised kernel matrixlearning by kernel propagation, " IEEE Trans. Neural Netw., vol. 21, no. 11, pp. 1831-1841, Nov. 2010.
28. M. Elad, Sparse and Redundant Representations-From Theory to Applicationsin Signal and Image Processing. New York, NY USA: Springer, 2010.
29. B. Scholkopf and A. Smola, Learning with Kernels-Support VectorMachines, Regularization, Optimization and Beyond. Cambridge, MA, USA: MIT Press, 2002.
30. M. Belkin, P. Niyogi., V. Sindhwani, "Manifold regularization: Ageometric framework for learning from labeled and unlabeled examples, "J. Mach. Learn. Res., vol. 7, pp. 2399-2434, Nov. 2006.
31. A. N. Tikhonov, "Regularization of incorrectly posed problems. Numer. Funct. Anal. Optim., vol. 21 no. 4, pp. 1624-1627, 1963.
32. S. Melacci and M. Belkin, "Laplacian support vector machines trained inthe primal, " J. Mach. Learn. Res., vol. 12, no. 3, pp. 1149-1184, Mar. 2011.
33. J. R. Shewchuk, "An introduction to the conjugate gradient methodwithout the agonizing pain, " School of Computer Science, CarnegieMellon University, Pittsburgh, PA, USA, Tech. Rep. CMU-CS-94-125, 1994.
34. J. A. Tropp, A. C. Gilbert., M. J. Strauss, "Algorithms for simultaneoussparse approximation. Part I: Greedy pursuit, " Signal Process., vol. 86, no. 3, pp. 572-588, Mar. 2006.
35. J. Yang, A. Bouzerdoum., S. Phung, "A training algorithm for sparseLS-SVM using compressive sampling, " in Proc. 2010 IEEE Int. Conf. Acoust. Speech Signal Process., 2010, Dallas, TX, USA, pp. 2054-2057.
36. B. Borchers, "CSDP, a C library for semidefinite programming, " Optim. Methods Softw., vol. 11, no. 1-4, pp. 613-623, 1999.
37. 2011. [Online]. Available: Http://www.ehu.eus/ccwintco/index.phptitle=Hyperspectral-Remote-Sensing-Scenes
38. J. A. Richards and X. Jia, Remote Sensing Digital Image Analysis: AnIntroduction, 4th ed. Berlin, Germany: Springer, 2006.