access icon free Combined FATEMD-based band selection method for hyperspectral images

Feature selection, which is called band selection for hyperspectral data, is widely used for hyperspectral images. A novel hyperspectral band selection method based on combined fast and adaptive tridimensional empirical mode decomposition (cFATEMD) is proposed in this study. The hyperspectral data is decomposed into a set of tridimensional intrinsic mode functions (TIMFs) and a residual (RES) by FATEMD, which can reduce high-frequency noise and signal. A stop condition of the decomposition is proposed based on the k-means clustering algorithm and the Dunn validity index, which can prevent excessive decomposition and make generated RES contain as much useful information as possible. In consideration of the useful information in decomposition results, these TIMFs and the RES are combined into a new data based on the spectral similarity between themselves and the original data. Four state-of-the-art band selection methods, cooperating with the proposed cFATEMD, are used to select bands by the new combined data. Several experiments are conducted on three publicly available hyperspectral datasets and the results are compared with corresponding methods’ results using the original data. Experimental results demonstrate that the proposed method yields great classification appearance.

Inspec keywords: remote sensing; pattern clustering; hyperspectral imaging; image classification; feature selection; geophysical image processing

Other keywords: residual; Dunn validity index; TIMF; hyperspectral data; hyperspectral band selection method; combined fast-and-adaptive tridimensional empirical mode decomposition; spectral similarity; RES; publicly available hyperspectral datasets; k-means clustering algorithm; cFATEMD; hyperspectral images; combined FATEMD-based band selection method; feature selection; tridimensional intrinsic mode functions

Subjects: Geography and cartography computing; Instrumentation and techniques for geophysical, hydrospheric and lower atmosphere research; Computer vision and image processing techniques; Data and information; acquisition, processing, storage and dissemination in geophysics; Image recognition; Geophysical techniques and equipment

References

    1. 1)
      • 5. Chen, C., Jiang, F., Yang, C., et al: ‘Hyperspectral classification based on spectral-spatial convolutional neural networks’, Eng. Appl. Artif. Intell., 2018, 68, pp. 165171.
    2. 2)
      • 38. He, Z., Li, J., Liu, L., et al: ‘Three-dimensional empirical mode decomposition (TEMD): a fast approach motivated by separable filters’, Signal Process., 2017, 131, pp. 307319.
    3. 3)
      • 27. Fleuret, F.: ‘Fast binary feature selection with conditional mutual information’, J. Mach. Learn. Res., 2004, 5, (3), pp. 15311555.
    4. 4)
      • 24. Yang, R., Su, L., Zhao, X., et al: ‘Representative band selection for hyperspectral image classification’, J. Vis. Commun. Image Represent., 2017, 48, pp. 396403.
    5. 5)
      • 16. Zhao, C., Wang, Y., Mei, F.: ‘Kernel ICA feature extraction for anomaly detection in hyperspectral imagery’, Chin. J. Electron., 2012, 21, (2), pp. 265269.
    6. 6)
      • 6. Zhao, J., Zhou, Y., Jia, T., et al: ‘Spectral-spatial classification of hyperspectral imagery with cooperative game’, ISPRS J. Photogramm. Remote Sens., 2018, 135, pp. 3142.
    7. 7)
      • 35. Ghosh, A., Datta, A., Ghosh, S., et al: ‘Self-adaptive differential evolution for feature selection in hyperspectral image data’, Appl. Soft Comput. J., 2013, 13, (4), pp. 19691977.
    8. 8)
      • 42. Feng, J., Jiao, L., Liu, F., et al: ‘Unsupervised feature selection based on maximum information and minimum redundancy for hyperspectral images’. Pattern Recognit., 2016, 51, pp. 295309.
    9. 9)
      • 18. Belkin, M., Niyogi, Y.: ‘Laplacian eigenmaps for dimensionality reduction and data representation’, Neural Comput., 2006, 15, (6), pp. 13731396.
    10. 10)
      • 29. Yang, C., Liu, S., Bruzzone, L., et al: ‘A semisupervised feature metric based band selection method for hyperspectral image classification’. Workshop on Hyperspectral Image and Signal Processing, Shanghai, China, June 2012, pp. 14.
    11. 11)
      • 20. Zhang, Z., Zhang, H.: ‘Nonlinear dimension reduction via local tangent space alignment’. Lecture Notes in Computer Science, Hong Kong, China, March 2003, pp. 477481.
    12. 12)
      • 26. Sun, W., Tian, L., Xu, Y., et al: ‘Fast and robust self-representation method for hyperspectral band selection’, IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., 2017, 10, (11), pp. 50875098.
    13. 13)
      • 4. Qiao, T., Ren, J., Sun, M., et al: ‘Effective compression of hyperspectral imagery using an improved 3D DCT approach for land-cover analysis in remote-sensing applications’, Int. J. Remote Sens., 2014, 35, (20), pp. 73167337.
    14. 14)
      • 11. Ren, J., Zabalza, J., Marshall, S., et al: ‘Effective feature extraction and data reduction in remote sensing using hyperspectral imaging’, IEEE Signal Process. Mag., 2014, 31, (4), pp. 149154.
    15. 15)
      • 8. Ahmad, M., Khan, A.M., Hussain, R.: ‘Graph-based spatial-spectral feature learning for hyperspectral image classification’, IET Image Process., 2017, 11, (12), pp. 13101316.
    16. 16)
      • 21. Zabalza, J., Ren, J., Ren, J.: ‘Structured covariance principal component analysis for real-time onsite feature extraction and dimensionality reduction in hyperspectral imaging’, Opt. Soc., 2014, 53, (20), pp. 44404449.
    17. 17)
      • 9. Zabalza, J., Ren, J., Yang, M., et al: ‘Novel folded-PCA for improved feature extraction and data reduction with hyperspectral imaging and SAR in remote sensing’, ISPRS J. Photogramm. Remote Sens., 2014, 93, (7), pp. 112122.
    18. 18)
      • 13. Sun, J., Liu, Y.: ‘The fusion arithmetic of multi-resolution remote sense image based on a modified fast independent component analysis’. Proc. Synthetic Aperture Radar, Huangshan, China, November 2007, pp. 342346.
    19. 19)
      • 30. Cao, X., Wei, C., Han, J., et al: ‘Hyperspectral band selection using improved classification map’. IEEE Geosci. Remote Sens. Lett., 2017, 14, (11), pp. 21472151.
    20. 20)
      • 37. Huang, N.E., Shen, Z., Long, S.R., et al: ‘The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis’, Proc. Math. Phys. Eng. Sci., 1998, 454, (1971), pp. 903995.
    21. 21)
      • 15. Fauvel, M., Chanussot, J., Benediktsson, J.A.: ‘Kernel principal component analysis for the classification of hyperspectral remote sensing data over urban areas’, EURASIP J. Adv. Signal Process., 2009, 2009, (1), pp. 114.
    22. 22)
      • 25. Zeng, X., Durrani, T.S.: ‘Band selection for hyperspectral images using copulas-based mutual information’. IEEE Workshop on Statistical Signal Processing Proc., Cardiff, UK, August 2009, pp. 341344.
    23. 23)
      • 19. Roweis, S.T., Saul, L.K.: ‘Nonlinear dimensionality reduction by locally linear embedding’, Science, 2000, 290, (5500), pp. 23232326.
    24. 24)
      • 17. Yang, G., Liu, H., Yu, X.: ‘Hyperspectral remote sensing image classification based on kernel Fisher discriminant analysis’. Proc. 2007 Int. Conf. Wavelet Analysis and Pattern Recognition, Beijing, China, November 2008, pp. 11391143.
    25. 25)
      • 40. Bhuiyan, S.M.A., Adhami, R.R., Khan, J.F.: ‘Fast and adaptive bidimensional empirical mode decomposition using order-statistics filter based envelope estimation’, EURASIP J. Adv. Signal Process., 2008, 2008, (1), pp. 118.
    26. 26)
      • 14. Jin, X., Scott, P., Harold, C.: ‘A comparative study of target detection algorithms for hyperspectral imagery’. Int. Society for Optical Engineering, Orlando, FL, USA, April 2009, pp. 112.
    27. 27)
      • 33. Sun, K., Geng, X., Ji, L., et al: ‘A new band selection method for hyperspectral image based on data quality’, IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., 2014, 7, (6), pp. 26972703.
    28. 28)
      • 41. Riffi, J., Mahraz, A.M., Abbad, A., et al: ‘3D extension of the fast and adaptive bidimensional empirical mode decomposition’, Multidimens. Syst. Signal Process., 2015, 26, (3), pp. 823834.
    29. 29)
      • 7. Guan, L., Xie, W., Pei, J.: ‘Segmented minimum noise fraction transformation for efficient feature extraction of hyperspectral images’, Pattern Recognit., 2015, 48, (10), pp. 32163226.
    30. 30)
      • 39. Nunes, J.C., Bouaoune, Y., Delechelle, E., et al: ‘Image analysis by bidimensional empirical mode decomposition’, Image Vis. Comput., 2003, 21, (12), pp. 10191026.
    31. 31)
      • 32. Jia, J., Yang, N., Zhang, C., et al: ‘Object-oriented feature selection of high spatial resolution images using an improved relief algorithm’, Math. Comput. Model., 2013, 58, (3–4), pp. 619626.
    32. 32)
      • 22. Yang, C., Tan, Y., Lorenzo, B., et al: ‘Discriminative feature metric learning in the affinity propagation model for band selection in hyperspectral images’, Remote Sens., 2017, 9, (8), pp. 116.
    33. 33)
      • 23. Cao, X., Li, X., Li, X., et al: ‘Hyperspectral band selection with objective image quality assessment’, Int. J. Remote Sens., 2017, 38, (12), pp. 36563668.
    34. 34)
      • 2. Wang, Y., Xue, J.: ‘Matched shrunken subspace detectors for hyperspectral target detection’, Neurocomputing, 2018, 272, pp. 226236.
    35. 35)
      • 1. Chen, G., Li, C., Sun, W.: ‘Hyperspectral face recognition via feature extraction and CRC-based classifier’, IET Image Process., 2017, 11, (4), pp. 266272.
    36. 36)
      • 3. Imani, M., Ghassemian, H.: ‘Edge patch image-based morphological profiles for classification of multispectral and hyperspectral data’, IET Image Process., 2016, 11, (3), pp. 164172.
    37. 37)
      • 28. Santos, L.C.B.D., Guimaraes, S.J.F., Santos, J.A.D., et al: ‘Efficient unsupervised band selection through spectral rhythms’, IEEE. J. Sel. Top. Signal. Process., 2017, 9, (6), pp. 10161025.
    38. 38)
      • 31. Peng, H., Long, F., Ding, C.: ‘Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy’. IEEE Trans. Pattern Anal. Mach. Intell., 2005, 27, (8), pp. 12261238.
    39. 39)
      • 34. Su, H., Du, Q., Chen, G., et al: ‘Optimized hyperspectral band selection using particle swarm optimization’, IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., 2014, 7, (6), pp. 26592670.
    40. 40)
      • 10. Wang, Y., Huang, S., Liu, Z., et al: ‘Locality preserving projection based on endmember extraction for hyperspectral image dimensionality reduction and target detection’, Appl. Spectrosc., 2016, 70, (9), pp. 15731581.
    41. 41)
      • 36. Li, Z., Jing, Z., Xia, L., et al: ‘A genetic algorithm based wrapper feature selection method for classification of hyperspectral images using support vector machine’. Int. Society for Optical Engineering, Guangzhou, China, June 2008, pp. 19.
    42. 42)
      • 12. Zhang, S.: ‘Studies of high spectral resolution atmospheric sounding data compression and noise reduction based on principal component analysis method’. Proc. Int. Congress on Image and Signal, Tianjin, China, October 2009, pp. 15.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-ipr.2018.5550
Loading

Related content

content/journals/10.1049/iet-ipr.2018.5550
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading