Abstract

The support vector machine (SVM) is a widely used approach for high-dimensional data classification. Traditionally, SVMs use features from the spectral bands of hyperspectral images with each feature contributing equally to the classification. In practical applications, although affected by noise, slight contributions can also be obtained from deteriorated bands. Thus, compared with feature reduction or equal assignment of weights to all the features, feature weighting is a trade-off choice. In this study, we examined two approaches to assigning weights to SVM features to increase the overall classification accuracy: (1) “CSC-SVM” refers to a support vector machine with compactness and a separation coefficient feature weighting algorithm, and (2) “SE-SVM” refers to a support vector machine with a similarity entropy feature weighting algorithm. Analyses were conducted on a public data set with nine selected land-cover classes. In comparison with traditional SVMs and other classical feature weighting algorithms, the proposed weighting algorithms increase the overall classification accuracy, and even better results could be obtained with few training samples.

© 2014 Optical Society of America

Full Article  |  PDF Article

References

  • View by:
  • |
  • |
  • |

  1. F. Melgani and L. Bruzzone, “Classification of hyperspectral remote sensing images with support vector machines,” IEEE Trans. Geosci. Remote Sens. 42, 1778–1790 (2004).
    [CrossRef]
  2. W. Li, S. Prasad, and J. E. Fowler, “Noise-adjusted subspace discriminant analysis for hyperspectral imagery classification,” IEEE Trans. Geosci. Remote Sens. 10, 1374–1378 (2013).
    [CrossRef]
  3. S. Prasad, M. Cui, W. Li, and J. E. Fowler, “Segmented mixture-of-Gaussian classfication for hyperspectral image analysis,” IEEE Trans. Geosci. Remote Sens. 11, 138–142 (2014).
    [CrossRef]
  4. P. Gurram and H. Kwon, “Sparse kernel-based ensemble learning with fully optimized kernel parameters for hyperspectral classfication problems,” IEEE Trans. Geosci. Remote Sens. 51, 787–802 (2013).
    [CrossRef]
  5. L. Guo, Y. Wu, L. Zhao, T. Cao, W. Yan, and X. Shen, “Classification of mental task from EEG signals using immune feature weighted support vector machines,” IEEE Trans. Magn. 47, 866–869 (2011).
    [CrossRef]
  6. P. Hsu, “Feature extraction of hyperspectral images using wavelet and matching pursuit,” ISPRS J. Photogramm. Remote Sens. 62, 78–92 (2007).
  7. A. M. Filippi, R. Archibald, B. L. Bhaduri, and E. A. Bright, “Hyperspectral agricultural mapping using support vector machine-based endmember extraction (SVM-BEE),” Opt. Express 17, 23823–23842 (2009).
    [CrossRef]
  8. C. Camps-Valls and L. Bruzzone, “Kernel-based methods for hyperspectral image classification,” IEEE Trans. Geosci. Remote Sens. 43, 1351–1362 (2005).
    [CrossRef]
  9. M. Marconcini, G. Camps-Valls, and L. Bruzzone, “A composite semisupervised svm for classification of hyperspectral images,” IEEE Trans. Geosci. Remote Sens. 6, 234–238 (2009).
    [CrossRef]
  10. Y. Bazi and F. Melgani, “Toward an optimal SVM classification system for hyperspectral remote sensing images,” IEEE Trans. Geosci. Remote Sens. 44, 3374–3385 (2006).
    [CrossRef]
  11. M. Fauvel, J. A. Benediktsson, J. Chanussot, and J. R. Sveinsson, “Spectral and spatial classification of hyperspectral data using SVMs and morphological profiles,” IEEE Trans. Geosci. Remote Sens. 46, 3804–3814 (2008).
    [CrossRef]
  12. F. A. Mianji and Y. Zhang, “SVM-based unmixing-to-classification conversion for hyperspectral abundance quantification,” IEEE Trans. Geosci. Remote Sens. 49, 4318–4327 (2011).
    [CrossRef]
  13. Y. Gu and K. Feng, “Optimized Laplacian SVM with distance metric learning for hyperspectral image classification,” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 6, 1109–1117 (2013).
  14. M. Pal and G. M. Foody, “Feature selection for classification of hyperspectral data by SVM,” IEEE Trans. Geosci. Remote Sens. 48, 2297–2307 (2010).
    [CrossRef]
  15. W. Li, S. Prasad, J. E. Fowler, and L. M. Bruce, “Locality-preserving dimensionality reduction and classification for hyperspectral image analysis,” IEEE Trans. Geosci. Remote Sens. 50, 1185–1198 (2012).
    [CrossRef]
  16. R. Huang and M. He, “Band selection based on feature weighting for classification of hyperspectral data,” IEEE Trans. Geosci. Remote Sens. 2, 156–159 (2005).
    [CrossRef]
  17. B. Qi, C. Zhao, E. Youn, and C. Nansen, “Use of weighting algorithms to improve traditional support vector machine based classifications of relflectance data,” Opt. Express 19, 26816–26826 (2011).
    [CrossRef]
  18. Y. Tarabalka, M. Fauvel, J. Chanussot, and J. A. Benediktsson, “SVM- and MRF-based method for accurate classification of hyperspectral images,” IEEE Trans. Geosci. Remote Sens. 7, 736–740 (2010).
    [CrossRef]
  19. A. A. Green, M. Berman, P. Switzer, and M. D. Craig, “A transformation for ordering multispectral data in terms of image quality with implications for noise removal,” IEEE Trans. Geosci. Remote Sens. 26, 65–74 (1988).
    [CrossRef]
  20. D. A. Landgrebe, Signal Theory Methods in Multispectral Remote Sensing (Wiley, 2003).
  21. B. Guo, S. R. Gunn, R. I. Damper, and J. D. B. Nelson, “Customizing kernel functions for SVM-based hyperspectral image classification,” IEEE Trans. Image Process. 17, 622–629 (2008).
    [CrossRef]
  22. C. Huang, L. S. Davis, and J. R. Townshend, “An assessment of support vector machines for land cover classification,” Int. J. Remote Sens. 23, 725–749 (2002).
    [CrossRef]
  23. C. A. Shah, P. Watanachaturaporn, M. K. Arora, and P. K. Varshney, “Some recent results on hyperspectral image classification,” in Proceedings of IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data (IEEE, 2003), pp. 346–353.
  24. J. Gualtieri and R. Cromp, “Support vector machines for hyperspectral remote sensing classification,” in Proceedings of 27th AIPR Workshop Advances in Computer Assisted Recognition (SPIE, 1998), pp. 121–132.

2014

S. Prasad, M. Cui, W. Li, and J. E. Fowler, “Segmented mixture-of-Gaussian classfication for hyperspectral image analysis,” IEEE Trans. Geosci. Remote Sens. 11, 138–142 (2014).
[CrossRef]

2013

P. Gurram and H. Kwon, “Sparse kernel-based ensemble learning with fully optimized kernel parameters for hyperspectral classfication problems,” IEEE Trans. Geosci. Remote Sens. 51, 787–802 (2013).
[CrossRef]

W. Li, S. Prasad, and J. E. Fowler, “Noise-adjusted subspace discriminant analysis for hyperspectral imagery classification,” IEEE Trans. Geosci. Remote Sens. 10, 1374–1378 (2013).
[CrossRef]

Y. Gu and K. Feng, “Optimized Laplacian SVM with distance metric learning for hyperspectral image classification,” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 6, 1109–1117 (2013).

2012

W. Li, S. Prasad, J. E. Fowler, and L. M. Bruce, “Locality-preserving dimensionality reduction and classification for hyperspectral image analysis,” IEEE Trans. Geosci. Remote Sens. 50, 1185–1198 (2012).
[CrossRef]

2011

F. A. Mianji and Y. Zhang, “SVM-based unmixing-to-classification conversion for hyperspectral abundance quantification,” IEEE Trans. Geosci. Remote Sens. 49, 4318–4327 (2011).
[CrossRef]

L. Guo, Y. Wu, L. Zhao, T. Cao, W. Yan, and X. Shen, “Classification of mental task from EEG signals using immune feature weighted support vector machines,” IEEE Trans. Magn. 47, 866–869 (2011).
[CrossRef]

B. Qi, C. Zhao, E. Youn, and C. Nansen, “Use of weighting algorithms to improve traditional support vector machine based classifications of relflectance data,” Opt. Express 19, 26816–26826 (2011).
[CrossRef]

2010

Y. Tarabalka, M. Fauvel, J. Chanussot, and J. A. Benediktsson, “SVM- and MRF-based method for accurate classification of hyperspectral images,” IEEE Trans. Geosci. Remote Sens. 7, 736–740 (2010).
[CrossRef]

M. Pal and G. M. Foody, “Feature selection for classification of hyperspectral data by SVM,” IEEE Trans. Geosci. Remote Sens. 48, 2297–2307 (2010).
[CrossRef]

2009

M. Marconcini, G. Camps-Valls, and L. Bruzzone, “A composite semisupervised svm for classification of hyperspectral images,” IEEE Trans. Geosci. Remote Sens. 6, 234–238 (2009).
[CrossRef]

A. M. Filippi, R. Archibald, B. L. Bhaduri, and E. A. Bright, “Hyperspectral agricultural mapping using support vector machine-based endmember extraction (SVM-BEE),” Opt. Express 17, 23823–23842 (2009).
[CrossRef]

2008

M. Fauvel, J. A. Benediktsson, J. Chanussot, and J. R. Sveinsson, “Spectral and spatial classification of hyperspectral data using SVMs and morphological profiles,” IEEE Trans. Geosci. Remote Sens. 46, 3804–3814 (2008).
[CrossRef]

B. Guo, S. R. Gunn, R. I. Damper, and J. D. B. Nelson, “Customizing kernel functions for SVM-based hyperspectral image classification,” IEEE Trans. Image Process. 17, 622–629 (2008).
[CrossRef]

2007

P. Hsu, “Feature extraction of hyperspectral images using wavelet and matching pursuit,” ISPRS J. Photogramm. Remote Sens. 62, 78–92 (2007).

2006

Y. Bazi and F. Melgani, “Toward an optimal SVM classification system for hyperspectral remote sensing images,” IEEE Trans. Geosci. Remote Sens. 44, 3374–3385 (2006).
[CrossRef]

2005

R. Huang and M. He, “Band selection based on feature weighting for classification of hyperspectral data,” IEEE Trans. Geosci. Remote Sens. 2, 156–159 (2005).
[CrossRef]

C. Camps-Valls and L. Bruzzone, “Kernel-based methods for hyperspectral image classification,” IEEE Trans. Geosci. Remote Sens. 43, 1351–1362 (2005).
[CrossRef]

2004

F. Melgani and L. Bruzzone, “Classification of hyperspectral remote sensing images with support vector machines,” IEEE Trans. Geosci. Remote Sens. 42, 1778–1790 (2004).
[CrossRef]

2002

C. Huang, L. S. Davis, and J. R. Townshend, “An assessment of support vector machines for land cover classification,” Int. J. Remote Sens. 23, 725–749 (2002).
[CrossRef]

1988

A. A. Green, M. Berman, P. Switzer, and M. D. Craig, “A transformation for ordering multispectral data in terms of image quality with implications for noise removal,” IEEE Trans. Geosci. Remote Sens. 26, 65–74 (1988).
[CrossRef]

Archibald, R.

Arora, M. K.

C. A. Shah, P. Watanachaturaporn, M. K. Arora, and P. K. Varshney, “Some recent results on hyperspectral image classification,” in Proceedings of IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data (IEEE, 2003), pp. 346–353.

Bazi, Y.

Y. Bazi and F. Melgani, “Toward an optimal SVM classification system for hyperspectral remote sensing images,” IEEE Trans. Geosci. Remote Sens. 44, 3374–3385 (2006).
[CrossRef]

Benediktsson, J. A.

Y. Tarabalka, M. Fauvel, J. Chanussot, and J. A. Benediktsson, “SVM- and MRF-based method for accurate classification of hyperspectral images,” IEEE Trans. Geosci. Remote Sens. 7, 736–740 (2010).
[CrossRef]

M. Fauvel, J. A. Benediktsson, J. Chanussot, and J. R. Sveinsson, “Spectral and spatial classification of hyperspectral data using SVMs and morphological profiles,” IEEE Trans. Geosci. Remote Sens. 46, 3804–3814 (2008).
[CrossRef]

Berman, M.

A. A. Green, M. Berman, P. Switzer, and M. D. Craig, “A transformation for ordering multispectral data in terms of image quality with implications for noise removal,” IEEE Trans. Geosci. Remote Sens. 26, 65–74 (1988).
[CrossRef]

Bhaduri, B. L.

Bright, E. A.

Bruce, L. M.

W. Li, S. Prasad, J. E. Fowler, and L. M. Bruce, “Locality-preserving dimensionality reduction and classification for hyperspectral image analysis,” IEEE Trans. Geosci. Remote Sens. 50, 1185–1198 (2012).
[CrossRef]

Bruzzone, L.

M. Marconcini, G. Camps-Valls, and L. Bruzzone, “A composite semisupervised svm for classification of hyperspectral images,” IEEE Trans. Geosci. Remote Sens. 6, 234–238 (2009).
[CrossRef]

C. Camps-Valls and L. Bruzzone, “Kernel-based methods for hyperspectral image classification,” IEEE Trans. Geosci. Remote Sens. 43, 1351–1362 (2005).
[CrossRef]

F. Melgani and L. Bruzzone, “Classification of hyperspectral remote sensing images with support vector machines,” IEEE Trans. Geosci. Remote Sens. 42, 1778–1790 (2004).
[CrossRef]

Camps-Valls, C.

C. Camps-Valls and L. Bruzzone, “Kernel-based methods for hyperspectral image classification,” IEEE Trans. Geosci. Remote Sens. 43, 1351–1362 (2005).
[CrossRef]

Camps-Valls, G.

M. Marconcini, G. Camps-Valls, and L. Bruzzone, “A composite semisupervised svm for classification of hyperspectral images,” IEEE Trans. Geosci. Remote Sens. 6, 234–238 (2009).
[CrossRef]

Cao, T.

L. Guo, Y. Wu, L. Zhao, T. Cao, W. Yan, and X. Shen, “Classification of mental task from EEG signals using immune feature weighted support vector machines,” IEEE Trans. Magn. 47, 866–869 (2011).
[CrossRef]

Chanussot, J.

Y. Tarabalka, M. Fauvel, J. Chanussot, and J. A. Benediktsson, “SVM- and MRF-based method for accurate classification of hyperspectral images,” IEEE Trans. Geosci. Remote Sens. 7, 736–740 (2010).
[CrossRef]

M. Fauvel, J. A. Benediktsson, J. Chanussot, and J. R. Sveinsson, “Spectral and spatial classification of hyperspectral data using SVMs and morphological profiles,” IEEE Trans. Geosci. Remote Sens. 46, 3804–3814 (2008).
[CrossRef]

Craig, M. D.

A. A. Green, M. Berman, P. Switzer, and M. D. Craig, “A transformation for ordering multispectral data in terms of image quality with implications for noise removal,” IEEE Trans. Geosci. Remote Sens. 26, 65–74 (1988).
[CrossRef]

Cromp, R.

J. Gualtieri and R. Cromp, “Support vector machines for hyperspectral remote sensing classification,” in Proceedings of 27th AIPR Workshop Advances in Computer Assisted Recognition (SPIE, 1998), pp. 121–132.

Cui, M.

S. Prasad, M. Cui, W. Li, and J. E. Fowler, “Segmented mixture-of-Gaussian classfication for hyperspectral image analysis,” IEEE Trans. Geosci. Remote Sens. 11, 138–142 (2014).
[CrossRef]

Damper, R. I.

B. Guo, S. R. Gunn, R. I. Damper, and J. D. B. Nelson, “Customizing kernel functions for SVM-based hyperspectral image classification,” IEEE Trans. Image Process. 17, 622–629 (2008).
[CrossRef]

Davis, L. S.

C. Huang, L. S. Davis, and J. R. Townshend, “An assessment of support vector machines for land cover classification,” Int. J. Remote Sens. 23, 725–749 (2002).
[CrossRef]

Fauvel, M.

Y. Tarabalka, M. Fauvel, J. Chanussot, and J. A. Benediktsson, “SVM- and MRF-based method for accurate classification of hyperspectral images,” IEEE Trans. Geosci. Remote Sens. 7, 736–740 (2010).
[CrossRef]

M. Fauvel, J. A. Benediktsson, J. Chanussot, and J. R. Sveinsson, “Spectral and spatial classification of hyperspectral data using SVMs and morphological profiles,” IEEE Trans. Geosci. Remote Sens. 46, 3804–3814 (2008).
[CrossRef]

Feng, K.

Y. Gu and K. Feng, “Optimized Laplacian SVM with distance metric learning for hyperspectral image classification,” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 6, 1109–1117 (2013).

Filippi, A. M.

Foody, G. M.

M. Pal and G. M. Foody, “Feature selection for classification of hyperspectral data by SVM,” IEEE Trans. Geosci. Remote Sens. 48, 2297–2307 (2010).
[CrossRef]

Fowler, J. E.

S. Prasad, M. Cui, W. Li, and J. E. Fowler, “Segmented mixture-of-Gaussian classfication for hyperspectral image analysis,” IEEE Trans. Geosci. Remote Sens. 11, 138–142 (2014).
[CrossRef]

W. Li, S. Prasad, and J. E. Fowler, “Noise-adjusted subspace discriminant analysis for hyperspectral imagery classification,” IEEE Trans. Geosci. Remote Sens. 10, 1374–1378 (2013).
[CrossRef]

W. Li, S. Prasad, J. E. Fowler, and L. M. Bruce, “Locality-preserving dimensionality reduction and classification for hyperspectral image analysis,” IEEE Trans. Geosci. Remote Sens. 50, 1185–1198 (2012).
[CrossRef]

Green, A. A.

A. A. Green, M. Berman, P. Switzer, and M. D. Craig, “A transformation for ordering multispectral data in terms of image quality with implications for noise removal,” IEEE Trans. Geosci. Remote Sens. 26, 65–74 (1988).
[CrossRef]

Gu, Y.

Y. Gu and K. Feng, “Optimized Laplacian SVM with distance metric learning for hyperspectral image classification,” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 6, 1109–1117 (2013).

Gualtieri, J.

J. Gualtieri and R. Cromp, “Support vector machines for hyperspectral remote sensing classification,” in Proceedings of 27th AIPR Workshop Advances in Computer Assisted Recognition (SPIE, 1998), pp. 121–132.

Gunn, S. R.

B. Guo, S. R. Gunn, R. I. Damper, and J. D. B. Nelson, “Customizing kernel functions for SVM-based hyperspectral image classification,” IEEE Trans. Image Process. 17, 622–629 (2008).
[CrossRef]

Guo, B.

B. Guo, S. R. Gunn, R. I. Damper, and J. D. B. Nelson, “Customizing kernel functions for SVM-based hyperspectral image classification,” IEEE Trans. Image Process. 17, 622–629 (2008).
[CrossRef]

Guo, L.

L. Guo, Y. Wu, L. Zhao, T. Cao, W. Yan, and X. Shen, “Classification of mental task from EEG signals using immune feature weighted support vector machines,” IEEE Trans. Magn. 47, 866–869 (2011).
[CrossRef]

Gurram, P.

P. Gurram and H. Kwon, “Sparse kernel-based ensemble learning with fully optimized kernel parameters for hyperspectral classfication problems,” IEEE Trans. Geosci. Remote Sens. 51, 787–802 (2013).
[CrossRef]

He, M.

R. Huang and M. He, “Band selection based on feature weighting for classification of hyperspectral data,” IEEE Trans. Geosci. Remote Sens. 2, 156–159 (2005).
[CrossRef]

Hsu, P.

P. Hsu, “Feature extraction of hyperspectral images using wavelet and matching pursuit,” ISPRS J. Photogramm. Remote Sens. 62, 78–92 (2007).

Huang, C.

C. Huang, L. S. Davis, and J. R. Townshend, “An assessment of support vector machines for land cover classification,” Int. J. Remote Sens. 23, 725–749 (2002).
[CrossRef]

Huang, R.

R. Huang and M. He, “Band selection based on feature weighting for classification of hyperspectral data,” IEEE Trans. Geosci. Remote Sens. 2, 156–159 (2005).
[CrossRef]

Kwon, H.

P. Gurram and H. Kwon, “Sparse kernel-based ensemble learning with fully optimized kernel parameters for hyperspectral classfication problems,” IEEE Trans. Geosci. Remote Sens. 51, 787–802 (2013).
[CrossRef]

Landgrebe, D. A.

D. A. Landgrebe, Signal Theory Methods in Multispectral Remote Sensing (Wiley, 2003).

Li, W.

S. Prasad, M. Cui, W. Li, and J. E. Fowler, “Segmented mixture-of-Gaussian classfication for hyperspectral image analysis,” IEEE Trans. Geosci. Remote Sens. 11, 138–142 (2014).
[CrossRef]

W. Li, S. Prasad, and J. E. Fowler, “Noise-adjusted subspace discriminant analysis for hyperspectral imagery classification,” IEEE Trans. Geosci. Remote Sens. 10, 1374–1378 (2013).
[CrossRef]

W. Li, S. Prasad, J. E. Fowler, and L. M. Bruce, “Locality-preserving dimensionality reduction and classification for hyperspectral image analysis,” IEEE Trans. Geosci. Remote Sens. 50, 1185–1198 (2012).
[CrossRef]

Marconcini, M.

M. Marconcini, G. Camps-Valls, and L. Bruzzone, “A composite semisupervised svm for classification of hyperspectral images,” IEEE Trans. Geosci. Remote Sens. 6, 234–238 (2009).
[CrossRef]

Melgani, F.

Y. Bazi and F. Melgani, “Toward an optimal SVM classification system for hyperspectral remote sensing images,” IEEE Trans. Geosci. Remote Sens. 44, 3374–3385 (2006).
[CrossRef]

F. Melgani and L. Bruzzone, “Classification of hyperspectral remote sensing images with support vector machines,” IEEE Trans. Geosci. Remote Sens. 42, 1778–1790 (2004).
[CrossRef]

Mianji, F. A.

F. A. Mianji and Y. Zhang, “SVM-based unmixing-to-classification conversion for hyperspectral abundance quantification,” IEEE Trans. Geosci. Remote Sens. 49, 4318–4327 (2011).
[CrossRef]

Nansen, C.

Nelson, J. D. B.

B. Guo, S. R. Gunn, R. I. Damper, and J. D. B. Nelson, “Customizing kernel functions for SVM-based hyperspectral image classification,” IEEE Trans. Image Process. 17, 622–629 (2008).
[CrossRef]

Pal, M.

M. Pal and G. M. Foody, “Feature selection for classification of hyperspectral data by SVM,” IEEE Trans. Geosci. Remote Sens. 48, 2297–2307 (2010).
[CrossRef]

Prasad, S.

S. Prasad, M. Cui, W. Li, and J. E. Fowler, “Segmented mixture-of-Gaussian classfication for hyperspectral image analysis,” IEEE Trans. Geosci. Remote Sens. 11, 138–142 (2014).
[CrossRef]

W. Li, S. Prasad, and J. E. Fowler, “Noise-adjusted subspace discriminant analysis for hyperspectral imagery classification,” IEEE Trans. Geosci. Remote Sens. 10, 1374–1378 (2013).
[CrossRef]

W. Li, S. Prasad, J. E. Fowler, and L. M. Bruce, “Locality-preserving dimensionality reduction and classification for hyperspectral image analysis,” IEEE Trans. Geosci. Remote Sens. 50, 1185–1198 (2012).
[CrossRef]

Qi, B.

Shah, C. A.

C. A. Shah, P. Watanachaturaporn, M. K. Arora, and P. K. Varshney, “Some recent results on hyperspectral image classification,” in Proceedings of IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data (IEEE, 2003), pp. 346–353.

Shen, X.

L. Guo, Y. Wu, L. Zhao, T. Cao, W. Yan, and X. Shen, “Classification of mental task from EEG signals using immune feature weighted support vector machines,” IEEE Trans. Magn. 47, 866–869 (2011).
[CrossRef]

Sveinsson, J. R.

M. Fauvel, J. A. Benediktsson, J. Chanussot, and J. R. Sveinsson, “Spectral and spatial classification of hyperspectral data using SVMs and morphological profiles,” IEEE Trans. Geosci. Remote Sens. 46, 3804–3814 (2008).
[CrossRef]

Switzer, P.

A. A. Green, M. Berman, P. Switzer, and M. D. Craig, “A transformation for ordering multispectral data in terms of image quality with implications for noise removal,” IEEE Trans. Geosci. Remote Sens. 26, 65–74 (1988).
[CrossRef]

Tarabalka, Y.

Y. Tarabalka, M. Fauvel, J. Chanussot, and J. A. Benediktsson, “SVM- and MRF-based method for accurate classification of hyperspectral images,” IEEE Trans. Geosci. Remote Sens. 7, 736–740 (2010).
[CrossRef]

Townshend, J. R.

C. Huang, L. S. Davis, and J. R. Townshend, “An assessment of support vector machines for land cover classification,” Int. J. Remote Sens. 23, 725–749 (2002).
[CrossRef]

Varshney, P. K.

C. A. Shah, P. Watanachaturaporn, M. K. Arora, and P. K. Varshney, “Some recent results on hyperspectral image classification,” in Proceedings of IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data (IEEE, 2003), pp. 346–353.

Watanachaturaporn, P.

C. A. Shah, P. Watanachaturaporn, M. K. Arora, and P. K. Varshney, “Some recent results on hyperspectral image classification,” in Proceedings of IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data (IEEE, 2003), pp. 346–353.

Wu, Y.

L. Guo, Y. Wu, L. Zhao, T. Cao, W. Yan, and X. Shen, “Classification of mental task from EEG signals using immune feature weighted support vector machines,” IEEE Trans. Magn. 47, 866–869 (2011).
[CrossRef]

Yan, W.

L. Guo, Y. Wu, L. Zhao, T. Cao, W. Yan, and X. Shen, “Classification of mental task from EEG signals using immune feature weighted support vector machines,” IEEE Trans. Magn. 47, 866–869 (2011).
[CrossRef]

Youn, E.

Zhang, Y.

F. A. Mianji and Y. Zhang, “SVM-based unmixing-to-classification conversion for hyperspectral abundance quantification,” IEEE Trans. Geosci. Remote Sens. 49, 4318–4327 (2011).
[CrossRef]

Zhao, C.

Zhao, L.

L. Guo, Y. Wu, L. Zhao, T. Cao, W. Yan, and X. Shen, “Classification of mental task from EEG signals using immune feature weighted support vector machines,” IEEE Trans. Magn. 47, 866–869 (2011).
[CrossRef]

IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens.

Y. Gu and K. Feng, “Optimized Laplacian SVM with distance metric learning for hyperspectral image classification,” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 6, 1109–1117 (2013).

IEEE Trans. Geosci. Remote Sens.

M. Pal and G. M. Foody, “Feature selection for classification of hyperspectral data by SVM,” IEEE Trans. Geosci. Remote Sens. 48, 2297–2307 (2010).
[CrossRef]

W. Li, S. Prasad, J. E. Fowler, and L. M. Bruce, “Locality-preserving dimensionality reduction and classification for hyperspectral image analysis,” IEEE Trans. Geosci. Remote Sens. 50, 1185–1198 (2012).
[CrossRef]

R. Huang and M. He, “Band selection based on feature weighting for classification of hyperspectral data,” IEEE Trans. Geosci. Remote Sens. 2, 156–159 (2005).
[CrossRef]

F. Melgani and L. Bruzzone, “Classification of hyperspectral remote sensing images with support vector machines,” IEEE Trans. Geosci. Remote Sens. 42, 1778–1790 (2004).
[CrossRef]

W. Li, S. Prasad, and J. E. Fowler, “Noise-adjusted subspace discriminant analysis for hyperspectral imagery classification,” IEEE Trans. Geosci. Remote Sens. 10, 1374–1378 (2013).
[CrossRef]

S. Prasad, M. Cui, W. Li, and J. E. Fowler, “Segmented mixture-of-Gaussian classfication for hyperspectral image analysis,” IEEE Trans. Geosci. Remote Sens. 11, 138–142 (2014).
[CrossRef]

P. Gurram and H. Kwon, “Sparse kernel-based ensemble learning with fully optimized kernel parameters for hyperspectral classfication problems,” IEEE Trans. Geosci. Remote Sens. 51, 787–802 (2013).
[CrossRef]

C. Camps-Valls and L. Bruzzone, “Kernel-based methods for hyperspectral image classification,” IEEE Trans. Geosci. Remote Sens. 43, 1351–1362 (2005).
[CrossRef]

M. Marconcini, G. Camps-Valls, and L. Bruzzone, “A composite semisupervised svm for classification of hyperspectral images,” IEEE Trans. Geosci. Remote Sens. 6, 234–238 (2009).
[CrossRef]

Y. Bazi and F. Melgani, “Toward an optimal SVM classification system for hyperspectral remote sensing images,” IEEE Trans. Geosci. Remote Sens. 44, 3374–3385 (2006).
[CrossRef]

M. Fauvel, J. A. Benediktsson, J. Chanussot, and J. R. Sveinsson, “Spectral and spatial classification of hyperspectral data using SVMs and morphological profiles,” IEEE Trans. Geosci. Remote Sens. 46, 3804–3814 (2008).
[CrossRef]

F. A. Mianji and Y. Zhang, “SVM-based unmixing-to-classification conversion for hyperspectral abundance quantification,” IEEE Trans. Geosci. Remote Sens. 49, 4318–4327 (2011).
[CrossRef]

Y. Tarabalka, M. Fauvel, J. Chanussot, and J. A. Benediktsson, “SVM- and MRF-based method for accurate classification of hyperspectral images,” IEEE Trans. Geosci. Remote Sens. 7, 736–740 (2010).
[CrossRef]

A. A. Green, M. Berman, P. Switzer, and M. D. Craig, “A transformation for ordering multispectral data in terms of image quality with implications for noise removal,” IEEE Trans. Geosci. Remote Sens. 26, 65–74 (1988).
[CrossRef]

IEEE Trans. Image Process.

B. Guo, S. R. Gunn, R. I. Damper, and J. D. B. Nelson, “Customizing kernel functions for SVM-based hyperspectral image classification,” IEEE Trans. Image Process. 17, 622–629 (2008).
[CrossRef]

IEEE Trans. Magn.

L. Guo, Y. Wu, L. Zhao, T. Cao, W. Yan, and X. Shen, “Classification of mental task from EEG signals using immune feature weighted support vector machines,” IEEE Trans. Magn. 47, 866–869 (2011).
[CrossRef]

Int. J. Remote Sens.

C. Huang, L. S. Davis, and J. R. Townshend, “An assessment of support vector machines for land cover classification,” Int. J. Remote Sens. 23, 725–749 (2002).
[CrossRef]

ISPRS J. Photogramm. Remote Sens.

P. Hsu, “Feature extraction of hyperspectral images using wavelet and matching pursuit,” ISPRS J. Photogramm. Remote Sens. 62, 78–92 (2007).

Opt. Express

Other

C. A. Shah, P. Watanachaturaporn, M. K. Arora, and P. K. Varshney, “Some recent results on hyperspectral image classification,” in Proceedings of IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data (IEEE, 2003), pp. 346–353.

J. Gualtieri and R. Cromp, “Support vector machines for hyperspectral remote sensing classification,” in Proceedings of 27th AIPR Workshop Advances in Computer Assisted Recognition (SPIE, 1998), pp. 121–132.

D. A. Landgrebe, Signal Theory Methods in Multispectral Remote Sensing (Wiley, 2003).

Cited By

OSA participates in CrossRef's Cited-By Linking service. Citing articles from OSA journals and other participating publishers are listed here.

Alert me when this article is cited.


Figures (5)

Fig. 1.
Fig. 1.

AVIRIS data set: (a) sample band of AVIRIS data set (band 120) and (b) corresponding average reflectance profiles.

Fig. 2.
Fig. 2.

Parameter selection for different classifiers. (a) SVM, (b) MNF-SVM, (c) DAFE-SVM, (d) DBFE-SVM, (e) CSC-SVM, and (f) SE-SVM.

Fig. 3.
Fig. 3.

Ground reference map and classification results. (a) Ground reference map, (b) classification result of SVM, (c) classification result of MNF-SVM, (d) classification result of DAFE-SVM, (e) classification result of DBFE-SVM, (f) classification result of CSC-SVM, and (g) classification result of SE-SVM.

Fig. 4.
Fig. 4.

Overall classification accuracy with different training sample size ratio. (a) Training sample size ratio=0.1, (b) training sample size ratio=0.2, (c) training sample size ratio=0.3, (d) training sample size ratio=0.4, (e) training sample size ratio=0.5, and (f) training sample size ratio=0.6.

Fig. 5.
Fig. 5.

Average overall classification accuracy with different training sample size ratio.

Tables (3)

Tables Icon

Table 1. Number of Training and Testing Pixels in Each Class

Tables Icon

Table 2. Comparison of Cohen Kappa Coefficients, Overall Classification Accuracies (%), and Classification Accuracies (%) Conducted by the SVM, MNF-SVM, DAFE-SVM, DBFE-SVM, CSC-SVM, and SE-SVM Algorithms Yielded on AVIRIS Data Set

Tables Icon

Table 3. Observation Values of |(Z¯μ0)/(S/n)| with Proposed Algorithms and Comparison Weighting Algorithms

Equations (25)

Equations on this page are rendered with MathJax. Learn more.

DW(i,k)=1αm1j=1αm(xi(k)x^jm(k))2=1αm1j=1αm(x^tm(k)x^jm(k))2i=1,,N,k=1,,d,
divW(k)=1Ni=1NDW(i,k)=1Mm=1M1αmt=1αm1αm1j=1αm(x^tm(k)x^jm(k))2=1Mm=1M1αm(αm1)t=1αmj=1αm(x^tm(k)x^jm(k))2,
DB(i,k)=1M1n=1nmM1αnj=1αn(xi(k)x^jn(k))2=1M1n=1nmM1αnj=1αn(x^tm(k)x^jn(k))2,
divB(k)=1Ni=1NDB(i,k)=1Mm=1M1αmt=1αm1M1n=1nmM1αnj=1αn(x^tm(k)x^jn(k))2=1M(M1)m=1Mn=1nmM1αmαnt=1αmj=1αn(x^tm(k)x^jn(k))2.
w(k)=divB(k)/divW(k),k=1,2,,d.
vm=1αmj=1αmx^jm,m=1,2,,M.
ϕm(i,k)=|1M1j=1jmM|xi2(k)vj2(k)||xi2(k)vm2(k)||1/2.
Φ=[Φ1,Φ2,,ΦN]T.
Φi=[ϕ1(i,1)ϕ1(i,2)ϕ1(i,d)ϕ2(i,1)ϕ2(i,2)ϕ2(i,d)ϕM(i,1)ϕM(i,2)ϕM(i,d)]M×d.
H(k)=l=1N×M(Φ(l,k)log(Φ(l,k))+(1Φ(l,k))log(1Φ(l,k))),
H=[H(1),H(2),,H(d)].
w(k)=1/H(k)max(1/H),k=1,2,,d.
f(x)=sgn(i=1NyiβiK(xi,x)+b).
K(x,y)=(xTy+1)e,
K(x,y)=exp(γ(xy)2).
KW(x,y)=(xTWTWy+1)e,
KW(x,y)=exp(γW(xy)2).
K(x,y)=exp(γ(xy)2).
H0:μ=μ0H1:μ>μ0,
L(θ)=(12πσ)nexp(i=1n(ziμ)22σ2).
L(θ0)=(12πσ)nexp(i=1n(ziμ0)22σ2).
Λ=L(θ0)L(θ)=exp(12σ2[i=1n(ziμ0)2i=1n(ziμ)2])=exp(n2σ2(μμ0)2),
Λ=L(θ0)L(θ)=exp(12|Z¯μ0S/n|2).
|Z¯μ0S/n|k.
P{|Z¯μ0S/n|k}=α.

Metrics