Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon free Edge patch image-based morphological profiles for classification of multispectral and hyperspectral data

Morphological profiles (MPs) are efficiently exploited for modelling the geometrical features of structures in a scene. They increase the discriminability between different classes. The degree of processing of images depends on the geometrical structure and shape of the used structure element (SE) in the transformation. Since the geometric structures of an image are not the same in the whole image, the use of a fixed shape for SE may not be so efficient. Thus, it is proposed to extract an edge patch image-based morphological profile (EPIMP), which considers SEs with different shapes for different areas of image. The used SE in each patch of image is corresponding to the shape (i.e. edge image) of that patch. The proposed method is experimented on both multispectral and hyperspectral images and the obtained results show that the proposed method is much more efficient than the conventional MPs. Moreover, the experiments show the superiority of EPIMP compared with some state-of-the-art spectral-spatial classification methods such as generalised composite kernel, multiple feature learning, weighted joint collaborative representation and multiple-structure-element non-linear multiple kernel learning.

References

    1. 1)
      • 26. Benediktsson, A., Aevar Palmason, J., Sveinsson, J.R.: ‘Classification of hyperspectral data from urban areas based on extended morphological profiles’, IEEE Trans. Geosci. Remote Sens., 2005, 43, (3), pp. 480491.
    2. 2)
      • 19. Li, W., Du, Q.: ‘Joint within-class collaborative representation for hyperspectral image classification’, IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens., 2014, 7, (6), pp. 22002208.
    3. 3)
      • 18. Li, W., Tramel, E.W., Prasad, S., et al: ‘Nearest regularized subspace for hyperspectral classification’, IEEE Trans. Geosci. Remote Sens., 2014, 52, (1), pp. 477489.
    4. 4)
      • 20. Xiong, M., Ran, Q., Li, W., et al: ‘Hyperspectral image classification using weighted joint collaborative representation’, IEEE Geosci. Remote Sens. Lett., 2015, 12, (6), pp. 12091213.
    5. 5)
      • 6. Imani, M., Ghassemian, H.: ‘Feature extraction using weighted training samples’, IEEE Geosci. Remote Sens. Lett., 2015, 12, (7), pp. 13871391.
    6. 6)
      • 31. Cohen, J.: ‘A coefficient of agreement from nominal scales’, Edu. Psychol. Meas., 1960, 20, (1), pp. 3746.
    7. 7)
      • 30. Chang, C., Linin, C.: ‘LIBSVM–a library for support vector machines’, 2008. Accessed December 2015. http://www.csie.ntu.edu.tw/~cjlin/libsvm.
    8. 8)
      • 21. Koosha, M., Hajsadeghi, K., Koosha, M.: ‘Fine logarithmic adaptive soft morphological algorithm for synthetic aperture radar image segmentation’, Image Process., 2014, 8, (2), pp. 90102.
    9. 9)
      • 10. Imani, M., Ghassemian, H.: ‘Two dimensional linear discriminant analysis for hyperspectral data’, Photogramm. Eng. Remote Sens., 2015, 81, (10), pp. 777786.
    10. 10)
      • 15. Rakotomamonjy, A., Bach, F., Canu, S., et al: ‘SimpleMKL’, J. Mach. Learn. Res., 2008, 9, pp. 24912521.
    11. 11)
      • 13. Zehtabian, A., Ghassemian, H.: ‘An adaptive pixon extraction technique for multispectral/hyperspectral image classification’, IEEE Geosci. Remote Sens. Lett., 2015, 12, (4), pp. 831835.
    12. 12)
      • 4. Camps-Valls, G., Bruzzone, L.: ‘Kernel-based methods for hyperspectral image classification’, IEEE Trans. Geosci. Remote Sens., 2005, 43, (6), pp. 13511362.
    13. 13)
      • 14. Camps-Valls, G., Gomez-Chova, L., Muoz-Mar, J., et al: ‘Composite kernels for hyperspectral image classification’, IEEE Geosci. Remote Sens. Lett., 2006, 3, (1), pp. 9397.
    14. 14)
      • 24. Márquez-Neila, P., Baumela, L., Alvarez, L.: ‘A morphological approach to curvature-based evolution of curves and surfaces’, IEEE Trans. Patt. Ana. Mac. Intel., 2014, 36, (1), pp. 217.
    15. 15)
      • 17. Li, J., Huang, X., Gamba, P., et al: ‘Multiple feature learning for hyperspectral image classification’, IEEE Trans. Geosci. Remote Sens., 2015, 53, (3), pp. 15921606.
    16. 16)
      • 9. Hosseini, S.A., Ghassemian, H.: ‘Rational function approximation for feature reduction in hyperspectral data’, Remote Sens. Lett., 2016, 7, (2), pp. 101110.
    17. 17)
      • 8. Imani, M., Ghassemian, H.: ‘Ridge regression-based feature extraction for hyperspectral data’, Int. J. Remote Sens., 2015, 36, (6), pp. 17281742.
    18. 18)
      • 32. Foody, G.M.: ‘Thematic map comparison: evaluating the statistical significance of differences in classification accuracy’, Photogramm. Eng. Remote Sens., 2004, 70, (5), pp. 627633.
    19. 19)
      • 16. Li, J., Marpu, P., Plaza, A., et al: ‘Generalized composite kernel framework for hyperspectral image classification’, IEEE Trans. Geosci. Remote Sens., 2013, 51, (9), pp. 48164829.
    20. 20)
      • 1. Cover, T., Hart, P.: ‘Nearest neighbor pattern classification’, IEEE Trans. Inf. Theory, 1967, 13, (1), pp. 2127.
    21. 21)
      • 29. Fukunaga, K.: ‘Introduction to statistical pattern recognition’ (Academic Press Inc., San Diego, 1990).
    22. 22)
      • 7. Imani, M., Ghassemian, H.: ‘Feature space discriminant analysis for hyperspectral data feature reduction’, ISPRS J. Photogramm. Eng. Remote Sens., 2015, 102, pp. 113.
    23. 23)
      • 23. Lei, T., Wang, Y., Wang, G., et al: ‘Multivariate mathematical morphology based on fuzzy extremum estimation’, Image Process., 2014, 8, (9), pp. 548558.
    24. 24)
      • 5. Liu, X., Wang, L., Zhang, J., et al: ‘Global and local structure preservation for feature selection’, IEEE Trans. Neural Netw. Learn. Syst., 2014, 25, (6), pp. 10831095.
    25. 25)
      • 28. Gu, Y., Liu, T., Jia, X., et al: ‘Nonlinear multiple kernel learning with multi-structure-element extended morphological profiles for hyperspectral image classification’, IEEE Trans. Geosci. Remote Sens., 2016, 54, (6), pp. 32353247.
    26. 26)
      • 25. Dalla Mura, M., Benediktsson, A., Waske, B., et al: ‘Morphological attribute profiles for the analysis of very high resolution images’, IEEE Trans. Geosci. Remote Sens., 2010, 48, (10), pp. 37473762.
    27. 27)
      • 27. Dalla Mura, M., Benediktsson, J.A., Waske, B., et al: ‘Extended profiles with morphological attribute filters for the analysis of hyperspectral data’, Int. J. Remote Sens., 2010, 31, (22), pp. 59755991.
    28. 28)
      • 11. Golipour, M., Ghassemian, H., Mirzapour, F.: ‘Integrating hierarchical segmentation maps with MRF prior for classification of hyperspectral images in a bayesian framework’, IEEE Trans. Geosci. Remote Sens., 2016, 54, (2), pp. 805816.
    29. 29)
      • 12. Heshmati, A., Gholami, M., Rashno, A.: ‘Scheme for unsupervised colour texture image segmentation using neutrosophic set and non-subsampled contourlet transform’, IET Image Process., 2016, 10, (6), pp. 464473.
    30. 30)
      • 3. Landgrebe, D.A.: ‘Signal theory methods in multispectral remote sensing’ (Wiley, Hoboken, NJ, 2003).
    31. 31)
      • 22. Benediktsson, J.A., Pesaresi, M., Arnason, K.: ‘Classification and feature extraction for remote sensing images from urban areas based on morphological transformations’, IEEE Trans. Geosci. Remote Sens., 2003, 41, (9), pp. 19401949.
    32. 32)
      • 2. Yang, H., Meer, F.V.D., Bakker, W., et al: ‘A back-propagation neural network for mineralogical mapping from AVIRIS data’, Int. J. Remote Sens., 1999, 20, (1), pp. 97110.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-ipr.2016.0421
Loading

Related content

content/journals/10.1049/iet-ipr.2016.0421
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
This is a required field
Please enter a valid email address