An ICA Mixture Model Based Approach for Sub-pixel Classification of Hyperspectral Data

  • N. Prabhu
  • Manoj K. Arora
  • R. Balasubramanian
  • Kapil Gupta
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 258)

Abstract

Hyperspectral sensors are capable of collecting information in hundreds of contiguous spectral bands to expand the capability of multispectral sensors that use tens of discrete spectral bands. The contiguous bands play a vital role in study of types of vegetation, minerals, forest and soil types. In this paper, an iteratively learning parameter algorithm has been implemented to classify the hyperspectral image in an unsupervised way. The methodology followed in learning the parameters of ICA mixture model (ICAMM) has been discussed and the proportionality constant has been fixed as 0.7 to obtain the linear transformation for estimating the class membership probability of each pixel of a hyperspectral data. The ICAMM algorithm models class distributions as non-Gaussian densities, has been employed for unsupervised classification. Here the data have been transformed into new space in which, the data are as independent as possible by exploiting higher order statistics. This algorithm produces an average overall accuracy of around 65 % and outperforms the conventional K-means clustering and ISODATA.

Keywords

Hyperspectral data ICAMM algorithm Kurtosis Parametric classifier Unsupervised classification 

References

  1. 1.
    Hughes, G.F.: On the mean accuracy of statistical pattern recognizers. IEEE Trans. Inf. Theory 14(1), 55–63 (1968)CrossRefGoogle Scholar
  2. 2.
    Jia, X., Richards, J.A.: Efficient maximum likelihood classification for imaging spectrometer data sets. IEEE Trans. Geosci. Remote Sens. 32(2), 274–281 (1994)CrossRefGoogle Scholar
  3. 3.
    Foody, G.M., Arora, M.K.: Incorporating mixed pixels in the training, allocation and testing stages of supervised classifications. Pattern Recogn. Lett. 17, 1389–1398 (1996)CrossRefGoogle Scholar
  4. 4.
    Kasetkasem, T., Arora, M.K., Varshney, P.K., Areekul, V.: Improving subpixel classification by incorporating prior information in linear mixture models. IEEE Trans. Geosci. Remote Sens. 49(3), 1001–1013 (2011)CrossRefGoogle Scholar
  5. 5.
    Chanussot, J., Benediktsson, J.A., Fauvel, M.: Classification of remote sensing images from urban areas using a fuzzy probabilistic model. IEEE Geosci. Remote Sens. Lett. 3(1), 40–44 (2006)CrossRefGoogle Scholar
  6. 6.
    Platt, J.C.: Probalilistic outputs for support vector machines and comparisons to regularized likelihood methods. In: Smola, A. et al. (ed.), Advances in Large Margin Classifiers. MIT Press, Cambridge (2000) Google Scholar
  7. 7.
    Xu, M., Watanachaturaporn, P., Varshney, P.K., Arora. M.K.: Decision tree regression for soft classification of remote sensing data. Remote Sens. Environ. 97(3), 322–336 (2005)Google Scholar
  8. 8.
    Cheng, Q., Varshney, P.K., Arora, M.K.: Logistic regression for feature selection and soft classification of remote sensing data. IEEE Geosci. Remote Sens. Lett. 3(4), 491–494 (2006)CrossRefGoogle Scholar
  9. 9.
    Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification, 2nd edn. Wiley, New York (2001)MATHGoogle Scholar
  10. 10.
    Shah, C.A., Varshney, P.K.: A higher order statistical approach to spectral unmixing of remote sensing imagery. In: Proceedings of Geoscience Remote Sensing Symposium, IGARSS’, vol. 2, pp. 1065–1068 (2004)Google Scholar
  11. 11.
    Yu, J., Chen, J., Rashid, M.M.: Multiway independent component analysis mixture model and mutual information based fault detection and diagnosis approach of multiphase batch processes. Process Syst. Eng. 59(8), 2761–2779 (2013). (Wiley Online Library AIChE Journal)Google Scholar
  12. 12.
    Hyvärinen, A., Oja, E.: Independent component analysis: algorithms and applications. Neural Netw. Official J. Int. Neural Netw. Soc. 13(4–5), 411–430 (2000)Google Scholar
  13. 13.
    Common, P.: Independent component analysis, a new concept? Signal Process 36, 287–314 (1994)CrossRefGoogle Scholar
  14. 14.
    Beckmann, C.F.: Modelling with independent components. NeuroImage 62, 891–901 (2012)CrossRefGoogle Scholar
  15. 15.
    Lee, T.W., Lewicki, M.S., Sejnowski, T.J.: ICA mixture models for unsupervised classification of non-gaussian classes and automatic context switching in blind signal separation. IEEE Trans. Pattern Anal. Mach. Learn. 22(10), 1078–1089 (2000)CrossRefGoogle Scholar
  16. 16.
    Shah, C.A., Arora, M.K., Robila, S.A., Varshney, P.K.: ICA mixture model based unsupervised classification of hyperspectral imagery. In: IEEE Computer Society Applications on Image Pattern Recognition Workshop, Proceedings, pp. 29–35 (2002)Google Scholar
  17. 17.
    Plumbley, M.D.: Algorithms for nonnegative independent component analysis. IEEE Trans. Neural Netw. 14(3), 534–543 (2003). (A publication of the IEEE Neural Networks Council)CrossRefGoogle Scholar
  18. 18.
    Shah, C., Arora, M., Varshney, P.: Unsupervised classification of hyperspectral data: an ICA mixture model based approach. Int. J. Remote Sens. 25(2), 481–487 (2004)CrossRefGoogle Scholar
  19. 19.
    Lee, T.W., Girolami, M., Sejnowski, T.J.: Independent component analysis using an extended informax algorithm for mixed sub-Gaussian and super-Gaussian sources. Neural Comput. 11(2), 417–441 (1999)CrossRefGoogle Scholar
  20. 20.
    Shah, C.A., Varshney, P.K.: A higher order statistical approach to spectral unmixing of remote sensing imagery. In: Geoscience and Remote Sensing Symposium, pp. 1065–1068 (2004)Google Scholar
  21. 21.
    Lee, T.W., Lewicki, M.S.: Unsupervised image classification, segmentation and enhancement using ICA mixture models. IEEE Trans. Image Process. 11(3), 270–279 (2002). (A publication of the IEEE Signal Processing Society)CrossRefGoogle Scholar
  22. 22.
    National Aeronautics and Space Administration: http://modis.gsfc.nasa.gov/about/specifications.php. MODIS Homepage
  23. 23.
    Story, M., Congalton, R.: Accuracy assessment: a user’s perspective. Photogramm. Eng. Remote Sens. 52(3), 397–399 (1986)Google Scholar
  24. 24.
    Congalton, R.G.: A review of assessing the accuracy of classifications of remotely sensed data. Remote Sens. Environ. 46, 35–46 (1991)CrossRefGoogle Scholar

Copyright information

© Springer India 2014

Authors and Affiliations

  • N. Prabhu
    • 1
  • Manoj K. Arora
    • 1
  • R. Balasubramanian
    • 2
  • Kapil Gupta
    • 2
  1. 1.Department of Civil EngineeringRoorkeeIndia
  2. 2.Department of MathematicsRoorkeeIndia

Personalised recommendations