Band Selection Using SIFT in Hyperspectral Images

  • Authors

    • M. R.Vimala Devi
    • S. Kalaivani
    https://doi.org/10.14419/ijet.v7i4.10.20698

    Received date: October 1, 2018

    Accepted date: October 1, 2018

    Published date: October 2, 2018

  • Band selection, Hyperspectral Image, Principal component analysis, Scale invariant feature transform, Spectral unmixing.

  • Abstract

    In this paper an approach for dimension reduction of the hyperspectral image using scale invariant feature transform (SIFT) is introduced. Due to high dimensionality of hyperspectral cubes, it is a very difficult task to select few informative bands from original hyperspectral remote sensing images. Band with maximum amount of non-redundant information are chosen using the dissimilarity matrix obtained from scale invariant feature transformed image. The performance of the dimension reduction technique is analyzed by implementing a post-processing technique named spectral un-mixing. Spectral unmixing is the process of extracting end members and generating their abundance maps. End members are extracted with these selected informative bands using N-FINDR and abundance maps are generated using fully constrained least square estimation. The simulation software used for implementation of algorithms is MATLAB. Qualitatively and quantitatively the proposed feature based approach has been analyzed with application to spectral unmixing by comparing with two well-known existing dimension reduction techniques namely principal Component Analysis and Linear Discriminant Analysis. Hyperspectral images finds application in astronomy, agriculture, geosciences and surveillance.

  • References

    1. Antonio Plaza, Chein-I Chang(2005),An improved N-FINDR Algo-rithm in implementation Algorithms and Technologies for Multi-spectral, Hyperspectral, and Ultraspectral Imagery XI, Proceedings of SPIE,162-171.
    2. Alina Zare and K. C. Ho (2014), “Endmember variability in hyper-spectral analysis: addressing spectral variability during spectral un-mixing”, IEEE Signal Processing Magazine 31, pp. 95-104.
    3. Alp Ertürk and Antonio Plaza (2015), “Informative change detec-tion by unmixing for hyperspectral images”, IEEE Geoscience and Remote Sensing Letters 12(6), pp.1252-1256.
    4. Barberis, G. Danese, F. Leoporati, A. Plaza and E. Torti (2013), “Real-time implementation of the vertex component analysis algo-rithm on GPUs”, IEEE Geoscience and Remote Sensing Letters 10(2), pp. 251-255.
    5. Chang-Ci,Wu ,Tsai CT (2011),Random N-finder end member ex-traction algorithms for hyperspectral imagery,IEEE transcations on image processing,Vol .20(3), pp.641-656.
    6. D. G. Lowe (2004),”Distinctive image features from scaleinvariant keypoints,” International Journal of Computer Vision, vol. 60(2), pp. 91-110.
    7. Inmaculada Dópido, Jun Li, Paolo Gamba and Antonio Plaza (2014), A New Hybrid Strategy Combining Semisupervised Classi-fication and Unmixing of Hyperspectral Data, IEEE Journal of Se-lected Topics In Applied Earth Observations and Remote Sensing, VOL. 7, No. 8.
    8. John P. Ferguson (1981), “An Introduction to Hyperspectral Imag-ing”, Photonics and Analytic Marketing Ltd,pp 100-110.
    9. J. M. P. Nascimento and J. M. Bioucas-Dias (2005), “Vertex com-ponent analysis: a fast algorithm to unmix hyperspectral data”, IEEE Trans. Geosci. and Remote Sensing 43(4),pp. 898-910.
    10. J. M. Bioucas-Dias, A. Plaza, N. Dobigeon, M. Parente, Q. Du, P. Gader and J. Chanussot (2012), “Hyperspectral unmixing overview: Geometrical, statistical, and sparse regression-based approaches”, IEEE J. Sel. Topics Appl. Earth Observations Remote Sensing 5(2),pp. 354-379.
    11. Jie Chen, Cedric Richard and Paul Honeine (2012), “Nonlinear un-mixing of hyperspectral data based on a linear-mixture/nonlinear-fluctuation model”, IEEE Trans. Signal Process. 1, pp. 480-492.
    12. Lei Yan, Sui-Hua Liu, Hui-Li-Liu, Xin Jing and Chengqi Cheng (2014), Two inverse processes: spectral reconstruction and pixel unmixing, 2014 Third International Workshop on Earth Observation and Remote Sensing Applications,pp.456-501
    13. Lodha,S.P.Kamapur(2014),”Dimension reduction for hyperspectral images”,International Journal of innovation in engineering and man-agement,IJAIEM,3(10).pp. 45-53.
    14. M. A. Veganzones, Guillaume Tochon, Mauro Dalla-Mura and A. J. Plaza (2014), Hyperspectral image segmentation using a new spec-tral unmixing based binary partition tree representation, IEEE Trans. Image Process. 23(8), pp.3574-3589.
    15. M.R.Vimala Devi,Dr.S.Kalaivani (2016),”A view on spectral un-mixing in hyperspectral images”,Far East Journal of Electronics and Communication, ,pp.23-32.
    16. N. Keshava and J. F. Mustard (2002), “Spectral unmixing”, IEEE Signal Processing Magazine 19, pp.44-57.
    17. Nirmal Keshava (2003), “A survey of spectral unmixing algo-rithms”, Lincoln Laboratory Journal 14(1), pp.55-78.
    18. Peg Shippert (1980), “Introduction to Hyperspectral Image Analy-sis”, Earth Science Applications Research Systems.
    19. Panagiotis Antonapolus,Nikos Nikolaidis,Ionninis pitas (2009),”Hierarchical face clustering using SIFT fetures”,IEEE In-ternational Conference on Mechtronics and Automation,pp. 234-240.
    20. Sergio Bernabe, Gabriel Martín,Guillermo Botella (2017),Parallel Implementation of a Full Hyperspectral Unmixing Chain Using OpenCL, IEEE Journal of Selected Topics in Applied Earth Obser-vations and Remote Sensing ,10(6).
    21. W. Hapke (1981),Bidirectional reflectance spectroscopy”,J. Ge-ophys. Res. 86, pp. 3039-3054.
    22. W. Bao, Q. Li, L. Xin and K. Qu (2016), Hyperspectral unmixing algorithm based on Nonnegative Matrix Factorization,2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Beijing, ,pp. 6982-6985.doi: 10.1109/IGARSS.2016.7730821.

  • Downloads

  • How to Cite

    R.Vimala Devi, M., & Kalaivani, S. (2018). Band Selection Using SIFT in Hyperspectral Images. International Journal of Engineering and Technology, 7(4.10), 28-33. https://doi.org/10.14419/ijet.v7i4.10.20698