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

Spectral-Spatial Method for Hyperspectral Image classification in Noisy Environment

Download as PDF

DOI: 10.23977/geors.2019.21002 | Downloads: 22 | Views: 2675


Pierre Delmas 1, Caroline Fossati 1, Salah Bourennane 1


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

Corresponding Author

Pierre Delmas


Target detection is an important issue in the HyperSpectral Image (HSI) processing field. However, current spectral-identification-based target detection algorithms are sensitive to the noise and most denoising algorithms cannot preserve small targets, therefore it is necessary to design a robust detection algorithm that can preserve small targets. Because the signal-dependent photonic noise has become as dominant as the signal-independent noise generated by the electronic circuitry in HSI data collected by new-generation hyperspectral sensors, the reduction of the additive signal-dependent photonic noise becomes the focus of the current research in this field. To reduce the opto-elctronic noise from HSIs, a new method is developed in this paper. Firstly, a pre-whitening procedure is proposed to whiten noise in HSIs. Secondly, a three-dimensional wavelet packet transform (3-WPT) in tensor form is presented to find different component tensors of HSI. Then, to jointly filter a component tensor in each mode, multiway Wiener filter (MWF) is introduced. Moreover, to determine the best transform level and basis of 3-WPT a risk function is proposed. The effectiveness of our method in classification is experimentally demonstrated on a real-world HSI acquired by airborne sensor.


Detection, multi-linear algebra, reduction, wavelet, hyperspectral image


Pierre Delmas, Caroline Fossati and Salah Bourennane, Spectral-Spatial Method for Hyperspectral Image classification in Noisy Environment, Geoscience and Remote Sensing (2019) Vol. 2: 25-40. DOI:


[1] Z. Liu, H. Wang, and Q. Li. Tongue tumor detection in medical hyperspectral images. Sensors 1 (2011) 162–174.
[2] S. Lewis, A. Hudak, R. Ottmar, P. Robichaud, L. Lentile, S. Hood, J. Cronan, and P. Morgan. Using hyperspectral imagery to estimate forest floor consumption from wildfire in boreal forests of alaska, usa. Int. J. Wildland Fire 2 (2011) 255–271.
[3] D. Landgrebe. Hyperspectral image data analysis. IEEE Signal Process. Mag. 1 (2002) 17–28.

[4] D. Muti and S. Bourennane. Survey on tensor signal algebraic filtering. Signal Process. 2 (2007) 237–249.

[5] J. Marot, C. Fossati, and S. Bourennane. Overview on advances in tensor data denoising methods. SIAM J. Matrix Anal. Appl. 3 (2008) 1172–1204.

[6] A. Soltani-Farani, H. R. Rabiee, and S. A. Hosseini. Spatial-aware dictionary learning for hyperspectral image classification. IEEE Trans. Geosci. Remote Sens. 1 (2015) 527–541.

[7] J. Kerekes and J. Baum. Hyperspectral imaging system modeling. Linc Lab. J. 1 (2003) 117–130.

[8] J. Kerekes and J. Baum. Full-spectrum spectral imaging system analytical model. IEEE Trans. Geosci. Remote Sens. 3 (2005) 571–580.

[9] B. Aiazzi, L. Alparone, A. Barducci, S. Baronti, P. Marcoinni, I. Pippi, and M. Selva. Noise modelling and estimation of hyperspectral data from airborne imaging spectrometers. Ann. Geophys. 1 (2006) 1–9.

[10] E. Christophe, D. Leger, and C. Mailhes. Quality criteria benchmark for hyperspectral imagery. IEEE Trans. Geosci. Remote Sens. 9 (2005) 2103–2114.

[11] N. Acito, M. Diani, and G. Corsini. Signal-dependent noise modeling and model parameter estimation in hyperspectral images. IEEE Trans. Geosci. Remote Sens. 8 (2011) 2957–2971.

[12] M. L. Uss, B. Vozel, V. V. Lukin, and K. Chehdi. Local signal-dependent noise variance estimation from hyperspectral textural images. IEEE J. Sel. Topics Signal Process. 3 (2011) 469–486.

[13] L. He, J. Li, C. Liu and S. Li. Recent Advances on Spectral-Spatial Hyperspectral Image Classification: An Overview and New Guidelines. IEEE Trans. Geosci. Remote Sens. 3 (2018) 1579–1597.

[14] N. Renard, S. Bourennane, and J. Blanc-Talon. Denoising and dimensionality reduction using multilinear tools for hyper-spectral images. IEEE Geosci. Remote Sens. Lett. 2 (2008) 138–142.
[15] D. Landgrebe. Signal theory methods in multispectral remote sensing. New Jersey: Wiley, (2003).

[16] L. Alparone, M. Selva, B. Aiazzi, S. Baronti, F. Butera, and L. Chiarantini. Signal-dependent noise modelling and estimation of new-generation imaging spectrometers. Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 09 ( 2009) 1–4.

[17] D. Muti and S. Bourennane. Multidimensional filtering based on a tensor approach. Signal Process. 12 (2005) 2338–2353.
[18] D. Muti and S. Bourennane. Multiway filtering based on fourth-order cumulants. EURASIP Appl. Signal Process. 7 (2005) 1147–1158.

[19] D. Muti, S. Bourennane, and J. Marot. Lower-rank tensor approximation and multiway filtering. SIAM J. Matrix Anal. Appl. 3 (2008) 1172–1204.

[20] D. Letexier and S. Bourennane. Noise removal from hyperspectral images by multidimensional filtering. IEEE Trans. Geosci. Remote Sens. 7 (2008) 2061–2069.

[21] L. De Lathauwer, B. De Moor, and J. Vandewalle. On the best rank-1 and rank-(r1, r2,..., rn) approximation of higher-order tensors. SIAM J. Matrix Anal. Appl. 4 (2000) 1324–1342.

[22] L. De Lathauwer and J. Vandewalle. Dimensionality reduction in higher-order signal processing and rank-(r1, r2,..., rn) reduction in multilinear algebra. SIAM J. Matrix Anal. Appl. 4 (2000) 1324–1342.

[23] N. Renard and S. Bourennane. Improvement of target detection methods by multiway filtering. IEEE Trans. Geosci. Remote Sens. 8 (2008) 2407–2417.

[24] S. Bourennane, C. Fossati, and A. Cailly. Improvement of target-detection algorithms based on adaptive three-dimensional filtering. IEEE Trans. Geosci. Remote Sens. 4 (2010) 1383–1395.

[25] I. Daubechies. Orthonormal bases of compactly supported wavelets. Commun. Pure Appl. Math. 7 (1988) 909–996.

[26] D. Donoho. De-noising by soft-thresholding. IEEE Trans. Inf. Theory 3 (1995) 613–627.

[27] D. Donoho and J. Johnstone. Ideal spatial adaptation by wavelet shrinkage. Biometrika 3 (1994) 425–455.

[28] D. Donoho and I. Johnstone. Adapting to unknown smoothness via wavelet shrinkage. J. Amer. Statist. Assoc. 432 (1995) 1200–1244.

[29] S. Chang, B. Yu, and M. Vetterli. Adaptive wavelet thresholding for image denoising and compression. IEEE Trans. Image Process. 9 (2000) 1532–1546.
[30] I. Atkinson, F. Kamalabadi, S. Mohan, and D. Jones. Wavelet-based 2-d multichannel signal estimation. Proc. IEEE IGARSS 2 (2003) 743–745.

[31] A. Pizurica and W. Philips. Estimating the probability of the presence of a signal of interest in multiresolution single-and multiband image denoising. IEEE Trans. Image Process. 3 (2006) 654–665.

[32] H. Othman and S. Qian. Noise reduction of hyperspectral imagery using hybrid spatial-spectral derivative-domain wavelet shrinkage. IEEE Trans. Geosci. Remote Sens. 2 (2006) 397–408.

[33] A. Cichocki, R. Zdunek, A. Phan, and S. Amari. Nonnegative matrix and tensor factorizations: applications to exploratory multi-way data analysis and blind source separation. New Jersey: Wiley, (2009).

[34] R. Coifman and M. Wickerhauser. Entropy-based algorithms for best basis selection. IEEE Trans. Inf. Theory 2 (1992) 713–718.

[35] X. Liu, S. Bourennane, and C. Fossati. Nonwhite noise reduction in hyperspectral images. IEEE Geosci. Remote Sens. Lett. 3 (2012) 368–372.

[36] R. Roger and J. Arnold. Reliably estimating the noise in aviris hyperspectral images. Int. J. Remote Sens. 10 (1996) 1951–1962.

[37] I. C. Chein and D. Qian. Estimation of number of spectrally distinct signal sources in hyperspectral imagery. IEEE Trans. Geosci. Remote Sens. 3 (2004) 608–619.

[38] S. Mallat. A theory for multiresolution signal decomposition: The wavelet representation. IEEE Trans. Pattern Anal. Mach. Intell. 7 (1989) 674–693.

[39] D. Donoho and I. Johnstone. Ideal denoising in an orthonormal basis chosen from a library of bases. Comptes Rendus del’Academie des Sciences-Serie I-Mathematique 12 (1994) 1317–1322.
[40] D. Landgrebe. Multispectral data analysis: A signal theory perspective,” Purdue Univ., West Lafayette, IN (1998).
[41] C.-C. Chang and C.-J. Lin. LIBSVM: A library for support vector machines. ACM Trans. Intell. Syst. Technol.2 (2011) 1–27:27.

[42] Q. Yuan, L. Zhang, and H. Shen. Hyperspectral image denoising employing a spectral-spatial adaptive total variation model. IEEE Trans. Geosci. Remote Sens. 99 (2012) 1–18.

Downloads: 316
Visits: 30113

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.