Education, Science, Technology, Innovation and Life
Open Access
Sign In

Improvement of Classification Based on Noise and Spectral Dimensionality Reduction for Hyperspectral Image

Download as PDF

DOI: 10.23977/geors.2018.11012 | Downloads: 29 | Views: 3684

Author(s)

Salah Bourennane 1, Caroline Fossati 1, Josselin Juan 1

Affiliation(s)

1 Aix Marseille Univ, CNRS, Centrale Marseille, Institut Fresnel, Marseille, France

Corresponding Author

Salah Bourennane

ABSTRACT

Hyperspectral image (HSI) classification requires spectral dimensionalityreduction and spatial filtering. While common dimensionality reduction and denoising methods use linear algebra, we propose a tensorial method to jointly achieve denoising and dimensionality reduction.
Firstly, we propose a new method for pre-whitening the noise (PW) in HSI. Then we propose a method based on quadtree decomposition adapted to tensor data in order to take into account the local image characteristics in the multi-way Wiener filter (LMWF) which performs both noise and spectral dimensionality reduction, referred to as PW-LMWFdr-(K1;K2;P3). Classification algorithm SVM is applied to the output of dimensionality and noise reduction methods to compare their efficiency: The proposed PW-LMWFdr-(K1;K2;P3), PW-MWFdr-(K1;K2;P3), PCAdr,MNFdr associated with Wiener filtering.

KEYWORDS

Classification, Tensor, Reduction, Hyperspectral image.

CITE THIS PAPER

Salah Bourennane, Caroline Fossati and Josselin Juan, Improvement of Classification Based on Noise and Spectral Dimensionality Reduction for Hyperspectral Image. Geoscience and Remote Sensing (2018) 1: 9-17.

REFERENCES

[1] D. Landgrebe, Hyperspectral image data analysis as a high dimensional signal processing problem, Special issue of the IEEE Signal Process. Magazine 1 (2002) 17-28.
[2] A. Hyvarinen, J. Karhunen, and E. Oja, Independent Component Analysis. John Wiley Sons (2001).
[3] A. Plaza, P. Martinez, J. Plaza, and R. Perez, Dimensionality reduction and classification of hyperspectral image data using sequences of extended morphological transformations, IEEE Trans. on Geosci. and Remote Sens. 3 (2005) 466-479.
[4] H.K. Aggarwal, A. Majumdar, Exploiting spatiospectral correlation for impulse denoising in hyperspectral images. J. Electron.Imaging 24 (2015) 013027.
[5] P. Meza, J.E. Pezoa, S.N. Torres, Multidimensional Striping Noise Compensation in Hyperspectral Imaging: Exploiting Hypercubes Spatial, Spectral, and Temporal Redundancy. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 9 (2016) 4428-4441.
[6] B. Rasti, M.O. Ulfarsson, P. Ghamisi, Automatic Hyperspectral Image Restoration Using Sparse and Low-Rank Modeling. IEEE Geosci. Remote Sens. Lett. (2017) 1-5.
[7] X. Liu, S. Bourennane, C. Fossati, Reduction of Signal-Dependent Noise From Hyperspectral Images for Target Detection. IEEE Trans. Geosci. Remote Sens. 52 (2014) 5396-5411.
[8] D. Manolakis, D. Marden, G. Shaw, Hyperspectral image processing for automatic target detection applications. Linc Lab. J.14 (2003) 79-116.
[9] M. Uss, B. Vozel, V. Lukin, K. Chehdi, Local signal-dependent noise variance estimation from hyperspectral textural images,IEEE Jounal of Selected Topics in Signal Proc. 5 (2011) 469-486.
[10] D. Letexier, S. Bourennane, J. Blanc-Talon, Nonorthogonal tensor matricization for hyperspectral image filtering. IEEE Trans. Geosci. Remote Sens. Lett. 5 (2008) 3-7.
[11] H. Song, G. Wang, K. Zhang, Hyperspectral image denoising via low-rank matrix recovery. Remote Sensing Letters 5 (2014) 872-881.
[12] T.G. Kolda, B.W. Bader, Tensor decompositions and applications. SIAM Review 51 (2009) 455-500.
[13] N. Renard, S. Bourennane, Improvement of target detection methods by multiway filtering, IEEE Trans. on Geosci. and Remote Sens. 8 (2008) 2407-2417.
[14] D. Muti, S. Bourennane, Survey on tensor signal algebraic filtering. Signal Process. 87 (2007) 237-249.
[15] R.E. Roger, Principal components transform with simple, automatic noise adjustment. International Journal of Remote Sensing 17 (1996) 2719-2727.
[16] O. Kuybeda, D. Malah, M. Barzohar, Rank estimation and redundancy reduction of high-dimensional noisy signals with preservation of rare vectors. IEEE Trans. on Signal Processing 55 (2007) 5579-5592.
[17] Z. Xiao, S. Bourennane, Constrained nonnegative matrix factorization and hyperspectral image dimensionality reduction. Remote Sensing Letters 5 ( 2014) 46-54.
[18] V.N. Vapnik, The nature of statistical learning Theory, New York: Springer-Verlag (1995).
[19] D. Muti, S. Bourennane, Survey on tensor signal algebraic filtering, Signal Processing 87 (2007) 237-249.
[20] C. Chang and Q. Du, Estimation of number of spectrally distinct signal sources in hyperspectral imagery, IEEE Trans. on Geosci. and Remote Sens. 3 (2004) 608-619.
[21] H. Samet, The quadtree and related hierarchical data structure, ACM Computing Surveys (1984) 188-260.
[22] R. Archibald, G. Fann, Feature selection and classification of hyperspectral images with support vector machines. IEEE Trans. Geosci. Remote Sens. 4 (2007) 674-677.

Downloads: 316
Visits: 30109

Sponsors, Associates, and Links


All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.