• DocumentCode
    582920
  • Title

    A fusion method of multi-spectral image and panchromatic image based on NSCT and IHS transform

  • Author

    Xue, Xiaorong ; Wang, Aimin ; Wang, Hongfu ; Xiang, Fang

  • Author_Institution
    Sch. of Comput. & Inf. Eng., Anyang Normal Univ., Anyang, China
  • fYear
    2012
  • fDate
    15-17 July 2012
  • Firstpage
    640
  • Lastpage
    643
  • Abstract
    An image fusion method of multi-spectral image and panchromatic image based on the nonsubsampled Contourlet transform (NSCT) is proposed by analyzing the design and implementation of the filter bands of the NSCT. The multi-spectral image is decomposed with the IHS (Intensity, Hue, Saturation) transform, and the I, H, S, component are gotten. The I component after treatment and the panchromatic image are decomposed with the NSCT. And then, the low-frequency coefficients and high-frequency coefficients for the fused image can be obtained by means of the fusion rules based on region variance and local energy respectively. Finally, the fused image is reconstructed by the inverse NSCT and IHS transform. The Experimental results show that the comprehensive performance of the method presented has increased in retaining the spectral information and spatial details, and better integration effect is achieved.
  • Keywords
    filtering theory; image fusion; image reconstruction; inverse transforms; spectral analysis; filter bands; fused image; fusion rules; high-frequency coefficients; image fusion method; image reconstruction; intensity-hue-saturation transform; inverse IHS transform; inverse NSCT transform; low-frequency coefficients; multispectral image; nonsubsampled Contourlet transform; panchromatic image; region variance; spectral information; Filter banks; Image edge detection; Image fusion; Remote sensing; Satellites; Wavelet transforms;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Intelligent Control and Information Processing (ICICIP), 2012 Third International Conference on
  • Conference_Location
    Dalian
  • Print_ISBN
    978-1-4577-2144-1
  • Type

    conf

  • DOI
    10.1109/ICICIP.2012.6391490
  • Filename
    6391490