Unsupervised feature selection using geometrical measures in prototype space for hyperspectral imagery

IEEE Transactions on Geoscience and Remote Sensing

Volumn 52, Issue 7, 2014, Pages 3774-3787

  Ghamary Asl, Mohsen ^a   Mobasheri, Mohammad Reza ^a   Mojaradi, Barat ^b  

^a K N TOOSI UNIVERSITY OF TECHNOLOGY   (Iran)

^b IRAN UNIVERSITY OF SCIENCE AND TECHNOLOGY   (Iran)

Author keywords

Hyperspectral imagery (HSI); optimal feature size; prototype space (PS); Unsupervised feature selection (FS)

Indexed keywords

REMOTE SENSING; SPECTROSCOPY;

CURSE OF DIMENSIONALITY; FEATURE SIZES; FEATURE/BAND SELECTIONS; HYPER-SPECTRAL IMAGERIES; HYPERSPECTRAL IMAGERY; PROTOTYPE SPACE (PS); UNSUPERVISED APPROACHES; UNSUPERVISED FEATURE SELECTION;

OPTIMIZATION;

ALGORITHM; CORRELATION; DATA ACQUISITION; EXPERIMENTAL STUDY; GEOMETRY; IMAGE ANALYSIS; OPTIMIZATION; VECTOR;

EID: 84896388438     PISSN: 01962892     EISSN: None     Source Type: Journal    
DOI: 10.1109/TGRS.2013.2275831     Document Type: Article

References (52)

1. B.-C. Kuo and D. A. Landgrebe, "Nonparametric weighted feature extractionfor classification," IEEE Trans. Geosci. Remote Sens., vol. 42, no. 5,pp. 1096-1105, May 2004.
2. J. Nascimento, "Unsupervised Hyperspectral Unmixing Ph.D. dissertation,Univ. Technica De Lisbon, Lisbon, Portugal, 2006.
3. S. Khazai, A. Safari, B. Mojaradi, and S. Homayouni, " Improving theSVDD approach to hyperspectral image classification IEEE Geosci.Remote Sens. Lett., vol. 9, no. 4, pp. 594-598, Jul. 2012.
4. D.Manolakis, D.Marden, and G. A. Shaw, " Hyperspectral image processingfor automatic target detection applications," Lincoln Lab. J., vol. 14,no. 1, pp. 79-116, 2003.
5. J. E.West, D.W. Messinger, E. J. Ientilucci, J. P. Kerekes, and J. R. Schott "Matched filter stochastic background characterization for hyperspectraltarget detection in Proc. SPIE, Bellingham, WA, USA, 2005, vol. 5806,pp. 1-12. (Pubitemid 41545055)
6. S. B. Serpico and G.Moserd, "Extraction of spectral channels from hyperspectralimages for classification purposes," IEEE Trans. Geosci. RemoteSens., vol. 45, no. 2, pp. 484-495, Feb. 2007. (Pubitemid 46183043)
7. M. Kudo and J. Sklansky, "Comparison of algorithms that select featuresfor pattern classifiers," Pattern Recognit., vol. 33, no. 1, pp. 25-41,Jan. 2000. (Pubitemid 32081876)
8. I. Guyon, S. Gunn, M. Nikravesh, and L. A. Zadeh, " Part I: Featureextraction fundamentals in Feature Extraction: Foundations and Applications.,1st ed. Berlin, Germany: Springer-Verlag, 2006, pp. 29-182.
9. A.Martnez-Us, F. Pla, J. M. Sotoca, and P. Garca-Sevilla "Comparisonof unsupervised band selection methods for hyperspectral imaging inProc. IbPRIA, Girona, Spain, 2007, vol. 4477, pp. 30-38.
10. Q. Du and H. Yang, "A similarity-based unsupervised band selection forhyperspectral image analysis IEEE Geosci. Remote Sens. Lett., vol. 5,no. 4, pp. 564-568, Oct. 2008.
11. I. T. Jolliffe, "Introduction in Principal Component Analysis, 2nd ed.New York, NY, USA: Springer-Verlag, 2002, pp. 1-9.
12. A. Hyvarinen and E. Oja, "Independent component analysis: Algorithmsand applications," Neural Netw., vol. 13, no. 4 5, pp. 411-430,Jun. 2000. (Pubitemid 30447427)
13. L. O. Jimenez-Rodriguez, E. Arzuaga-Cruz, and M. Velez-Reyes "Unsupervisedlinear feature-extraction methods and their effects in theclassification of high-dimensional data IEEE Trans. Geosci. RemoteSens., vol. 45, no. 2, pp. 469-483, Feb. 2007. (Pubitemid 46183042)
14. A. A. Green, M. Berman, P. Switzer, and M. D. Craig, " A transformationfor ordering multispectral data in terms of image quality with implicationsfor noise removal IEEE Trans. Geosci. Remote Sens., vol. 26, no. 1,pp. 65-74, Jan. 1988. (Pubitemid 18596008)
15. S. Kaewpijit, J. Le Moigne, and T. El-Ghazawi, " Automatic reductionof hyperspectral imagery using wavelet spectral analysis," IEEE Trans.Geosci. Remote Sens., vol. 41, no. 4, pp. 863-871, Apr. 2003.
16. X. Huang and L. Zhang, "An adaptive mean-shift analysis approach forobject extraction and classification from urban hyperspectral imagery,"IEEE Trans. Geosci. Remote Sens., vol. 46, no. 12, pp. 4173-4185,Dec. 2008.
17. L. Zhang and X. Huang, "Object-oriented subspace analysis for airbornehyperspectral remote sensing imagery," Neurocomputing, vol. 73, no. 4- 6,pp. 927-936, Jan. 2010.
18. K. Fukunaga, "Random vectors and their properties in Introduction toStatistical Pattern Recognition, 2nd ed. New York, NY, USA: Springer-Verlag, 1990, pp. 11-50.
19. S. Theodoridis and K. Koutroumbas, "Feature selection," in PatternRecognition, 2nd ed. Athens, Greece: Dept. Informat. Telecommun.,Univ. Athens, 2003, pp. 163-205.
20. P. Bajcsy and P. Groves, "Methodology for hyperspectral band selection,"Photogramm. Eng. Remote Sens. J., vol. 70, no. 7, pp. 793-802, Jul. 2004. (Pubitemid 39081750)
21. B. Guo, S. R. Gunn, R. I. Damper, and J. D. B. Nelson, " Band selectionfor hyperspectral image classification using mutual information IEEEGeosci. Remote Sens. Lett., vol. 3, no. 4, pp. 522-526, Oct. 2006. (Pubitemid 44679664)
22. P. Mitra, C. A. Murthy, and S. K. Pal, "Unsupervised feature selectionusing feature similarity IEEE Trans. Pattern Anal. Mach. Intell., vol. 24,no. 3, pp. 301-312, Mar. 2002.
23. P. A. Devijver and J. Kittler, "Introduction to feature selection and extraction,"in Pattern Recognition: A Statistical Approach. Englewood Cliffs,NJ, USA: Prentice-Hall, 1982, ch. 5.
24. C.-I. Chang, Q. Du, T.-L. Sun, and M. L. G. Althouse, " A joint bandprioritization and band decorrelation approach to band selection for hyperspectralimage classification IEEE Trans. Geosci. Remote Sens., vol. 37,no. 6, pp. 2631-2641, Nov. 1999. (Pubitemid 30519596)
25. H. Du, H. Qi, X. Wang, R. Ramanath, and W. E. Snyder "Band selectionusing independent component analysis for hyperspectral imageprocessing," in Proc. 32nd Appl. Imag. Pattern Recognit.Workshop, 2003,pp. 93-98.
26. S. Jia, Y. Qian, J. Li, W. Liu, and Z. Ji, "Feature extraction and selectionhybrid algorithm for hyperspectral imagery classification," in Proc. IEEEIntern. Geosci. Remote Sens. Symp., Honolulu, HI, USA, 2010, pp. 72-75.
27. J. Basak, R. K. De, and S. K. Pal, "Unsupervised feature selection using aneuro-fuzzy approach," Pattern Recognit. Lett., vol. 19, no. 11, pp. 997-1006, Sep. 1998. (Pubitemid 128426764)
28. Y. Li and Z. F. Wu, "Fuzzy feature selection based on min-max learningrule and extension matrix," Pattern Recognit., vol. 41, no. 1, pp. 217-226,Jan. 2008. (Pubitemid 47284220)
29. M. L. Raymer, W. F. Punch, E. D. Goodman, E. D. Kuhn, and L. A. Jain"Dimensionality reduction using genetic algorithm," IEEE Trans. Evol.Comput., vol. 4, no. 2, pp. 164-171, Jul. 2000.
30. L. Zhang, Y. Zhong, B. Huang, J. Gong, and P. Li, " Dimensionality reductionbased on clonal selection for hyperspectral imagery IEEE Trans.Geosci. Remote Sens., vol. 45, no. 12, pp. 4172-4186, Dec. 2007. (Pubitemid 350157849)
31. C. Cariou, K. Chehdi, and S. Le Moan, "BandClust: An unsupervisedband reduction method for hyperspectral remote sensing IEEE Geosci.Remote Sens. Lett., vol. 8, no. 3, pp. 565-569, May 2011.
32. Q. Du and H. Yang, "Unsupervised band selection for hyperspectralimage analysis," in Proc. IEEE Int. Geosci. Remote Sens. Symp., 2007,pp. 282-285.
33. X. Huang, L. Zhang, and P. Li, "Classification and extraction of spatialfeatures in urban areas using high resolution multispectral imagery IEEEGeosci. Remote Sens. Lett., vol. 4, no. 2, pp. 260-264, Apr. 2007. (Pubitemid 46645144)
34. R. N. Clark, G. A. Swayze, K. E. Livo, R. F. Kokaly, S. J. Sutley,J. B. Dalton, R. R. McDougal, and C. A. Gent, "Imaging spectroscopy:Earth and planetary remote sensing with the USGS Tetracorder and expertsystems " J. Geophysical Res. Planet, vol. 108, no. E12, pp. 1-5,Dec. 2003.
35. M. R. Mobasheri and M. Ghamary Asl. (2011, Nov.). Classification bydiagnosing all absorption features (CDAF) for the most abundant mineralsin airborne hyperspectral images. EURASIP J. Adv. Signal Process. [Online]. 2011, p. 102. Available: http://asp.eurasipjournals.com/content/pdf/1687-6180-2011- 102.pdf
36. L.Wang, X. Jia, and Y. Zhang, "A novel geometry-based feature-selectiontechnique for hyperspectral imagery," IEEE Geosci. Remote Sens. Lett.,vol. 4, no. 1, pp. 171-175, Jan. 2007. (Pubitemid 46180279)
37. M. E.Winter, "N-FINDR: An algorithm for fast autonomous spectral endmemberdetermination in hyperspectral data," in Proc. SPIE-Im agingSpectrom. V, Denver, CO, USA, 1999, vol. 3753, pp. 266-275.
38. C.-I. Chang, "Target abundance-constrained subpixel detection in HyperspectralImaging: Techniques for Spectral Detection and Classification.New York, NY, USA: Kluwer, 2003, pp. 41-43.
39. D. C. Heinz and C.-I. Chang, "Fully constrained least squares linear spectralmixture analysis method for material quantification in hyperspectralimagery IEEE Trans. Geosci. Remote Sens., vol. 39, no. 3, pp. 529-545,Mar. 2001. (Pubitemid 32400422)
40. H. Yang and Q. Du, "Unsupervised hyperspectral band selection usingparallel processing," in Proc. IEEE Int. Geosci. Remote Sens. Symp.,2009, vol. 5, pp. V-80-V-83.
41. H. Yang, Q. Du, and G. Chen, "Unsupervised hyperspectral band selectionusing graphics processing units," IEEE J. Sel. Topics Appl. Earth Observ.,vol. 4, no. 3, pp. 660-668, Sep. 2011.
42. B. Mojaradi, H. Abrishami Moghadam, M. J. Valadan Zoej, andR. P. W. Duin, "Dimensionality reduction of hyperspectral data via spectralfeature extraction IEEE Trans. Geosci. Remote Sens., vol. 47, no. 7,pp. 2091-2105, Jul. 2009.
43. J. M. Bioucas-Dias and J. M. P. Nascimento, "Hyperspectral subspaceidentification," IEEE Trans. Geosci. Remote Sens., vol. 46, no. 8,pp. 2435-2445, Aug. 2008.
44. Jul. 2013. [Online]. Available: https://engineering.purdue.edu/~biehl/ MultiSpec/hyperspectral.html
45. Jul. 2013. [Online]. Available: www.csr.utexas.edu/hyperspectral/data/ Botswana
46. S. Rajan, J. Ghosh, and M. M. Crawford, "Exploiting class hierarchies forknowledge transfer in hyperspectral data IEEE Trans. Geosci. RemoteSens., vol. 44, no. 11, pp. 3408-3417, Nov. 2006. (Pubitemid 44711682)
47. M. Friedman, "The use of ranks to avoid the assumption of normalityimplicit in the analysis of variance " J. Amer. Stat. Assoc., vol. 32, no. 200,pp. 675-701, Dec. 1937.
48. M. Friedman, "Comparison of alternative tests of significance for theproblem of m rankings" Ann. Math. Stat., vol. 11, no. 1, pp. 86-92,Mar. 1940.
49. C.-I. Chang and Q. Du, "Estimation of number of spectrally distinct signalsources in hyperspectral imagery IEEE Trans. Geosci. Remote Sens.,vol. 42, no. 3, pp. 608-619, Mar. 2004.
50. R. Roger and J. Arnold, "Reliably estimating the noise in AVIRIS hyperspectralimagers," Int. J. Remote Sens., vol. 17, no. 10, pp. 1951-1962,Jul. 1996.
51. Jul. 2013. [Online]. Available: http://www.lx.it.pt/~bioucas/code/demo- HySime.zip
52. Jul. 2013. [Online]. Available: http://speclab.cr.usgs.gov/PAPERS/ cuprite.gr.truth.1992/swayze.1992.html