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

access icon free Improved neural network classification of hyperspectral imagery using weighted genetic algorithm and hierarchical segmentation

© The Institution of Engineering and Technology
Received 15/06/2018, Accepted 23/07/2019, Revised 25/03/2019, Published 01/08/2019

This study proposes a modified spectral–spatial classification approach for improving the spectral–spatial classification of hyperspectral images. The spatial information is obtained by an enhanced marker-based hierarchical segmentation (MHS) algorithm. The weighted genetic (WG) algorithm is first employed to obtain the subspace of hyperspectral data. The obtained features are then fed into the multi-layer perceptron (MLP) neural network classification algorithm. Afterwards, the MHS algorithm is applied in order to increase the accuracy of less-accurately classified land-cover types. In the proposed approach, namely MLP-MHS, the markers are extracted from the classification maps obtained by MLP and support vector machine classifiers. Experiments on two benchmark hyperspectral datasets, Pavia University and Berlin, validate the soundness of the proposed approach compared to the MLP and the original MHS algorithms.

Inspec keywords: feature extraction; image segmentation; neural nets; image classification; support vector machines; multilayer perceptrons; pattern classification; geophysical image processing; genetic algorithms

Other keywords: weighted genetic algorithm; spatial information; modified spectral–spatial classification approach; hyperspectral images; enhanced marker-based hierarchical segmentation algorithm; improved neural network classification; hyperspectral data; classification maps; multilayer perceptron neural network classification algorithm; MHS algorithm; hyperspectral imagery; benchmark hyperspectral datasets; MLP-MHS; original MHS algorithms

Subjects: Optical, image and video signal processing; Image recognition; Other topics in statistics; Optimisation techniques; Geophysics computing; Computer vision and image processing techniques; Geophysical techniques and equipment; Instrumentation and techniques for geophysical, hydrospheric and lower atmosphere research; Knowledge engineering techniques; Optimisation techniques; Neural computing techniques; Data and information; acquisition, processing, storage and dissemination in geophysics

References

    1. 1)
      • 25. Congalton, R.: ‘A review of assessing the accuracy of classifications of remotely sensed data’, Remote Sens. Environ., 1991, 37, pp. 35–46.
    2. 2)
      • 21. Kuo, B., Landgrebe, D.A.: ‘Nonparametric weighted feature extraction for classification’, IEEE Trans. Geosci. Remote Sens., 2004, 42, (5), pp. 1096–1105.
    3. 3)
      • 16. Soille, P.: ‘Morphological image analysis’ (Springer-Verlag, Berlin, Germany, 2003, 2nd edn.).
    4. 4)
      • 1. Carleer, A.P., Wolff, E.: ‘Urban land cover multi-level region-based classification of VHR data by selecting relevant features’, Int. J. Remote Sens., 2006, 27, (6), pp. 1035–1051.
    5. 5)
      • 22. Chang, C., Lin, C.: ‘LIBSVM – a library for support vector machines’, 2008.
    6. 6)
      • 20. Zheng, C., Huang, D., Shang, L.: ‘Feature selection in independent component subspace for microarray data classification’, Neurocomputing, 2006, 69, pp. 2407–2410.
    7. 7)
      • 23. Wu, T.-F., Lin, C.-J., Weng, R.C.: ‘Probability estimates for multiclass classification by pairwise coupling’, J. Mach. Learn. Res., 2004, 5, pp. 975–1005.
    8. 8)
      • 15. Tilton, J.: ‘Image segmentation by region growing and spectral clustering with a natural convergence criterion’. Proc. IGARSS'98, Seattle, WA, USA, 1998, 4, pp. 1766–1768.
    9. 9)
      • 7. Huang, X., Zhang, L.: ‘A multidirectional and multiscale morphological index for automatic building extraction from mutispectral GeoEye-1 imagery’, Photogramm. Eng. Remote Sens., 2011, 77, pp. 721–732.
    10. 10)
      • 10. Tarabalka, Y., Chanussot, J., Benediktsson, J.A.: ‘Segmentation and classification of hyperspectral images using minimum spanning forest grown from automatically selected markers’, IEEE Trans. Syst. Man Cybern. B, Cybern., 2010, 40, (5), pp. 1267–1279.
    11. 11)
      • 2. Jensen, J.R.: ‘Introductory digital image processing – a remote sensing perspective’ (Pearson Prentice-Hall, Upper Saddle River, NJ, 2004, 3rd edn.).
    12. 12)
      • 3. Shackelford, A.K., Davis, C.H.: ‘A combined fuzzy pixel-based and object-based approach for classification of high-resolution multispectral data over urban areas’, IEEE Trans. Geosci. Remote Sens., 2003, 41, pp. 2354–2363.
    13. 13)
      • 13. Gonzalez, R., Woods, R.: ‘Digital image processing’ (Prentice-Hall, Englewood Cliffs, NJ, 2002, 2nd edn.).
    14. 14)
      • 6. Fauvel, M., Chanussot, J., Benediktsson, J.A.: ‘A spatial–spectral kernel-based approach for the classification of remote sensing images’, Pattern Recognit., 2012, 45, pp. 381–392.
    15. 15)
      • 18. Landgrebe, D.A.: ‘Signal theory methods in multispectral remote sensing’ (Wiley, Hoboken, NJ, 2003).
    16. 16)
      • 5. Blaschke, T., Hay, G.J., Kelly, M., et al: ‘Geographic object-based image analysis – towards a new paradigm’, ISPRS J. Photogramm. Remote Sens., 2014, 87, pp. 180–191.
    17. 17)
      • 24. Camps-Valls, G., Bruzzone, L.: ‘Kernel-based methods for hyperspectral image classification’, IEEE Trans. Geosci. Remote Sens., 2005, 43, pp. 1351–1362.
    18. 18)
      • 8. Negri, R.G., Dutra, L.V., Sant'Anna, S.J.-S.: ‘An innovative support vector machine based method for contextual image classification’, ISPRS J. Photogramm. Remote Sens., 2014, 87, pp. 241–248.
    19. 19)
      • 11. Camps-Valls, G., Gomez-Chova, L., Munoz-Mari, J., et al: ‘Composite kernels for hyperspectral image classification’, IEEE Geosci. Remote Sens. Lett., 2006, 3, pp. 93–97.
    20. 20)
      • 19. Srivastava, A., Liu, X.: ‘Tools for application-driven linear dimension reduction’, Neurocomputing, 2005, 67, pp. 136–160.
    21. 21)
      • 17. Tarabalka, Y., Tilton, J.C., Benediktsson, J.A., Chanussot, J.A.: ‘Marker-based approach for the automated selection of a single segmentation from a hierarchical set of image segmentations’, IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., 2011, 5, pp. 262–272.
    22. 22)
      • 12. Fauvel, M., Chanussot, J., Benediktsson, J.A., et al: ‘Spectral and spatial classification of hyperspectral data using SVMs and morphological profiles’, IEEE Trans. Geosci. Remote Sens., 2008, 46, pp. 3804–3814.
    23. 23)
      • 9. Paneque-Gálvez, J., Mas, J.-F., Moré, G., et al: ‘Enhanced land use/cover classification of heterogeneous tropical landscapes using support vector machines and textural homogeneity’, Int. J. Appl. Earth Obs. Geoinf., 2013, 23, pp. 372–383.
    24. 24)
      • 14. Tilton, J.: ‘Analysis of hierarchically related image segmentations’. Proc. IEEE Workshop Advances in Techniques for Analysis of Remotely Sensed Data, Greenbelt, MD, USA, 2003, pp. 60–69.
    25. 25)
      • 4. Argüello, F., Heras, D.B.: ‘ELM-based spectral–spatial classification of hyperspectral images using extended morphological profiles and composite feature mappings’, Int. J. Remote Sens., 2015, 36, (2), pp. 645–664.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-ipr.2018.5693
Loading

Related content

content/journals/10.1049/iet-ipr.2018.5693
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Print this page
This is a required field
Please enter a valid email address