Journal Title : International Journal of Modern Trends in Engineering and Science


Author’s Name : K Sunil Manohar Reddyunnamed

Volume 04 Issue 03 2017

ISSN no:  2348-3121

Page no: 84-86

Abstract – The Hyper spectral images provide the images with hundreds of narrow contiguous spectral channels. The spectral information provided by the hyper spectral images is high when compared to the other class of remote sensing images such as panchromatic, multispectral images. Even though the hyper spectral images contain sufficient spectral information but processing and exploiting the hyper spectral data is considered as challenging task because of its high dimensionality. Data redundancy is one of the problems when processing hyper spectral data. And some bands in hyper spectral images are noisy and some bands are set to zero. So when we use all the bands for processing it increases the computational complexity in terms of storage and processing time. Because of this problem Dimensionality reduction techniques must be applied before we use it for processing. With that we can map high dimensionality of hyper spectral image data to lower dimensions without losing much of spectral features provided by the original hyper spectral data cube. Many techniques are developed for this dimensionality reduction; three of those techniques are analyzed in this paper

KeywordsDimensionality Reduction, Hyper spectral, Band Selection, Principal Component Analysis, Minimum Noise Fraction, Independent Component Analysis


  1. Yang, He, et al. “An efficient method for supervised hyperspectral band selection.” Geoscience and Remote Sensing Letters, IEEE 8.1 (2011): 138-142.
  2. Pal, Mahesh, and Giles M. Foody. “Feature selection for classification of hyperspectral data by SVM.” Geoscience and Remote Sensing, IEEE Transactions on 48.5 (2010): 2297-2307.
  3. Koonsanit, Kitti, Chuleerat Jaruskulchai, and Apisit Eiumnoh. “Band selection  for dimension reduction in hyper spectral image using integrated information gain and principal components analysis technique.” International Journal of Machine Learning and Computing 2.3 (2012): 248.
  4. K Burgers, Kate, et al. “A comparative analysis of dimension reduction algorithms on hyperspectral data.” LAMDA Research Group (2009): 1-23.
  5. Chang, Chein-I., and Haleh Safavi. “Progressive dimensionality reduction by transform for hyperspectral imagery.” Pattern Recognition 44.10 (2011): 2760-2773.
  6. Du, Qian, and He Yang. “Similarity-based unsupervised band selection for hyperspectral image analysis.” Geoscience and Remote Sensing Letters, IEEE 5.4 (2008): 564-568.
  7. Bruce, Lori Mann, et al. “Spectral reduction image processing techniques.” Geoscience and Remote Sensing Symposium, 2003. IGARSS’03. Proceedings. 2003.
  8. Rodarmel, Craig, and Jie  Shan.  “Principal  component analysis for hyperspectral image classification.” Surveying and Land Information Science 62.2 (2002): 115.
  9. Wang, Jing, and Chein-I. Chang. “Independent component analysis-based dimensionality reduction with applications in hyperspectral image analysis.” Geoscience and Remote Sensing, IEEE Transactions on 44.6 (2006): 1586-1600.
  10. A. A. Green, M. Berman, P. Switzer and M.  D. Craig, “A transformation for ordering multispectral data in terms of image quality with implications for noise removal,” in IEEE Transactions on Geoscience and Remote Sensing, vol. 26, no. 1, pp. 65-74, Jan 1988.
  11. Gao, Bo-Cai, et al. “Atmospheric correction algorithms for hyperspectral remote sensing data   of land and ocean.” Remote Sensing of Environment 113 (2009): S17-S24.