The Effect of Correlation on Determining the Intrinsic Dimension of a Hyperspectral Image

@article{CawseNicholson2013TheEO,
  title={The Effect of Correlation on Determining the Intrinsic Dimension of a Hyperspectral Image},
  author={Kerry Cawse-Nicholson and Amandine Robin and Michael Sears},
  journal={IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing},
  year={2013},
  volume={6},
  pages={482-487}
}
Determining the intrinsic dimension of a hyperspectral image is an important step in the spectral unmixing process and under- or over-estimation of this number may lead to incorrect unmixing for unsupervised methods. Most methods for estimating the intrinsic dimension require an estimate of the noise in the image, and noise estimates are often inaccurate in the presence of spectrally correlated noise. Since hyperspectral images are known to contain such correlated noise, intrinsic dimension… CONTINUE READING

References

Publications referenced by this paper.
Showing 1-10 of 26 references

Exploration of methods for estimation of number of endmembers in hyperspectral imagery

  • C.-C. Wu, W. Liu, C.-I Chang
  • Proc. SPIE, 2006, vol. 7, no. 43, pp. 1–11.
  • 2006
Highly Influential
4 Excerpts

Detection of subpixel spectral signatures in hyperspectral image sequences

  • J. C. Harsanyi, W. Farrand, C.-I Chang
  • inASPRS, 1994, pp. 236–247.
  • 1994
Highly Influential
4 Excerpts

Using random matrix theory to determine the intrinsic dimension of a hyperspectral image

  • K. Cawse-Nicholson
  • Ph.D. dissertation, Univ. Witwatersrand…
  • 2012
2 Excerpts

Principles and Theory for Data Mining and Machine

  • B. Clarke, E. Fokoué, H. H. Zhang
  • New York: Springer,
  • 2009
1 Excerpt

Similar Papers

Loading similar papers…