Abstract
In this chapter, we propose blind source separation methods to extract stellar spectra from hyperspectral images. The presented work particularly concerns astrophysical data cubes from the multi-unit spectroscopic explorer (MUSE) European project. These data cubes here consist of a spectrally and spatially transformed version of the light signals emitted by dense fields of stars, due to the influence of atmosphere and of the MUSE instrument, which is modelled by the so-called point spread function (PSF). The spectrum associated with each pixel of these data cubes can thus result from contributions of different star signals. We first derive the associated mixing model, taking into account the PSF properties. We then propose two separation methods based on the non-negativity of observed data, source spectra and mixing parameters. The first method is based on non-negative matrix factorization (NMF). The second one, which is the principal contribution in this chapter, uses the proposed parametric modelling of the mixing operator and performs alternate estimation steps for the star spectra and PSF parameters. Several versions of this method are proposed, in order to eventually combine good estimation accuracy and reduced computational load. Tests are performed with simulated but realistic data. The separation method based on parametric modelling gives very satisfactory performance.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
Our work is part of the Dedicated Algorithms for HyperspectraL Imaging in Astronomy (DAHLIA) project, funded by the French ANR agency, which aims at developing such methods.
- 2.
Hubble is a spatial telescope in orbit around the Earth since 1990. It is coupled with many spectrometers. This permits it to cover a spectral domain spreading from the infra-red to near ultra-violet wavelengths.
- 3.
Integrating the LSF over the whole spectrum or just over the interval \([\lambda -K,\lambda +K]\) is the same because the LSF is equal to zero outside this interval.
- 4.
We call (6.6) a “convolution” but note that it is a misnomer because, due to the spectral variability of the PSF, this integral does not correspond to the usual definition of a convolution.
- 5.
A monomial (or generalised permutation) matrix is a matrix in each row and column of which there is exactly one non-zero element.
- 6.
- 7.
In real operation, the variance estimates will be provided by the data reduction software (DRS) of MUSE.
- 8.
The FSF matrix to which we add the noise, and which is used for initialisation, is in fact an average matrix of the L true matrices of FSF corresponding to the considered spectral interval, since this FSF matrix is assumed to be constant in the interval by our LSQ-NMF method, but in reality it depends on the wavelength.
- 9.
The removed spectral bands correspond to a very noisy zone, since it has been used for the calibration with a laser star.
- 10.
We use: \( \dfrac{\partial (a^{-x})}{\partial x} = - a^{-x} \ln (a)\).
References
P. Comon, C. Jutten, Handbook of Blind Source Separation, Independent Component Analysis and Applications (Academic Press, Oxford, 2010)
A. Hyvärinen, J. Karhunen, E. Oja, Independent Component Analysis, Adaptive and Learning Systems for Signal Processing, Communications and Control (Wiley, New York, 2001)
C. Jutten, J. Herault, Blind separation of sources, part I: an adaptive algorithm based on neuromimetic architecture. Signal Process. 24(1), 1–10 (1991)
P. Comon, Independent component analysis, a new concept? Signal Process. 36(3), 287–314 (1994)
A. Hyvärinen, Fast and robust fixed-point algorithms for independent component analysis. IEEE Trans. Neural Netw. 10(3), 626–634 (1999)
M. Babaie-Zadeh, C. Jutten, A general approach for mutual information minimization and its application to blind source separation. Signal Process. 85(5), 975–995 (2005)
R. Gribonval, S. Lesage, A survey of sparse component analysis for blind source separation: principles, perspectives, and new challenges, in Proceedings of the ESANN (2006), pp. 323–330
F. Abrard, Y. Deville, A time-frequency blind signal separation method applicable to underdetermined mixtures of dependent sources. Signal Process. 85(7), 1389–1403 (2005)
I. Meganem, Y. Deville, M. Puigt, Blind separation methods based on correlation for sparse possibly-correlated images, in Proceedings of IEEE International Conference ICASSP, Dallas, USA (2010)
O. Yilmaz, S. Rickard, Blind separation of speech mixtures via time-frequency masking. IEEE Trans. Signal Process. 52, 1830–1847 (2004)
Y. Deville, M. Puigt, Temporal and time-frequency correlation-based blind source separation methods. part I: determined and underdetermined linear instantaneous mixtures. Signal Process. 87(3), 374–407 (2007)
A. Cichocki, R. Zdunek, A.H. Phan, S.-I. Amari, Nonnegative Matrix and Tensor Factorizations: Applications to Exploratory Multi-Way Data Analysis and Blind Source Separation (Wiley, Chichester, 2009)
P. Paatero, U. Tapper, Positive matrix factorization: a non-negative factor model with optimal utilization of error estimates of data values. Environmetrics 5(2), 111–126 (1994)
D. D. Lee, H. S. Seung, Algorithms for non-negative matrix factorization, in Proceedings of the NIPS, vol. 13 (MIT Press, 2001)
C.-J. Lin, Projected gradient methods for nonnegative matrix factorization. Neural Comput. 19, 2756–2779 (2007)
R. Zdunek, A. Cichocki, Fast nonnegative matrix factorization algorithms using projected gradient approaches for large-scale problems. Comput. Intell. Neurosci. 2008, 3:1–3:13 (2008)
K.H. Knuth, A Bayesian approach to source separation, in Proceedings of the First International Workshop on Independent Component Analysis and Signal Separation: ICA (1999), pp. 283–288
S. Moussaoui, D. Brie, A. Mohammad-Djafari, C. Carteret, Separation of non-negative mixture of non-negative sources using a Bayesian approach and MCMC sampling. IEEE Trans. Signal Process. 54(11), 4133–4145 (2006)
A. Selloum, Y. Deville, H. Carfantan, Separation of stellar spectra from hyperspectral images using particle filtering constrained by a parametric spatial mixing model, in Proceedings of IEEE ECMSM (2013)
D. Serre, E. Villeneuve, H. Carfantan, L. Jolissaint, V. Mazet, S. Bourguignon, A. Jarno, Modeling the spatial PSF at the VLT focal plane for MUSE WFM data analysis purpose, in SPIE Proceedings of Astronomical Telescopes and Instrumentation
J.M. Bioucas-Dias, A. Plaza, N. Dobigeon, M. Parente, Q. Du, P. Gader, J. Chanussot, Hyperspectral unmixing overview: geometrical, statistical, and sparse regression-based approaches. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 5(2), 354–379 (2012)
V.P. Pauca, J. Piper, R.J. Plemmons, Nonnegative matrix factorization for spectral data analysis. Linear Algebra Appl. 416, 29–47 (2006)
C. Fevotte, N. Bertin, J.-L. Durrieu, Nonnegative matrix factorization with the itakura-saito divergence: with application to music analysis. Neural Comput. 21, 793–830 (2009)
B. Gao, W.L. Woo, S.S. Dlay, Variational regularized 2-d nonnegative matrix factorization. IEEE Trans. Neural Netw. Learn. Syst. 23(5), 703–716 (2012)
D.C. Heinz, C.-I. Chang, Fully constrained least squares linear spectral mixture analysis method for material quantification in hyperspectral imagery. IEEE Trans. Geosci. Remote Sens. 39(3), 529–545 (2001)
L. Miao, H. Qi, Endmember extraction from highly mixed data using minimum volume constrained nonnegative matrix factorization. IEEE Trans. Geosci. Remote Sens. 45(3), 765–777 (2007)
J. Rapin, J. Bobin, J.-L. Starck, Sparse and non-negative bss for noisy data. IEEE Trans. Signal Process. 61(22), 5620–5632 (2013)
N. Gillis, R.J. Plemmons, Sparse nonnegative matrix underapproximation and its application to hyperspectral image analysis. Linear Algebra Appl. 438, 3991–4007 (2013)
Q. Zhang, H. Wang, R.J. Plemmons, V.P. Pauca, Tensor methods for hyperspectral data analysis: a space object material identification study. J. Opt. Soc. Am. A 25(12), 3001–3012 (2008)
N. Gillis, R.J. Plemmons, Dimensionality reduction, classification, and spectral mixture analysis using non-negative underapproximation. Opt. Eng. 50(2), 027001 (2011)
D.L. Donoho, V. Stodden, When does non-negative matrix factorization give a correct decomposition into parts?, in Proceedings of the NIPS (MIT Press, 2003)
S. Moussaoui, D. Brie, J. Idier, Non-negative source separation: range of admissible solutions and conditions for the uniqueness of the solution, in Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP, vol. 5 (2005), pp. 289–292
N. Gillis, Sparse and unique nonnegative matrix factorization. J. Mach. Learn. Res. 13, 3349–3386 (2012)
K. Huang, N.D. Sidiropoulos, A. Swami, Non-negative matrix factorization revisited: uniqueness and algorithm for symmetric decomposition. IEEE Trans. Signal Process. 62(1), 211–224 (2014)
G. Casalino, N.D. Buono, C. Mencar, Subtractive clustering for seeding non-negative matrix factorizations. Inf. Sci. 257, 369–387 (2014)
I. Meganem, Y. Deville, S. Hosseini, H. Carfantan, M. Karoui, Extraction of stellar spectra from dense fields in hyperspectral MUSE data cubes using non-negative matrix factorization, in Proceedings of IEEE international Workshop WHISPERS, Lisbon, Portugal (2011)
I. Meganem, S. Hosseini, Y. Deville, Positivity-based separation of stellar spectra using a parametric mixing model, in Proceedings of the 21th European Signal Processing Conference (EUSIPCO), Marrakech, Morocco (2013)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendix
Appendix
We can write
Derivation of (6.14) with respect to matrix \(\varvec{M}\) gives
Calculation with respect to \(\alpha \) then reads
The same type of expression is obtained for \(\beta \):
To compute \(\dfrac{\varvec{\partial M}}{\varvec{\partial \alpha }}\) and \(\dfrac{\varvec{\partial M}}{\varvec{\partial \beta }}\), we use the expression of \(M_{ki}\) as a function of \((\alpha ,\beta )\), given by Eq. (6.10). To simplify notations, as the star positions do not depend on \((\alpha ,\beta )\), we introduce \(Z = ||p_k-z_i|| _{F}^2 \) in expression (6.10).
This gives, for \(\alpha \):
And calculation for \(\beta \) readsFootnote 10
Rights and permissions
Copyright information
© 2016 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Meganem, I., Hosseini, S., Deville, Y. (2016). Separation of Stellar Spectra Based on Non-negativity and Parametric Modelling of Mixing Operator. In: Naik, G. (eds) Non-negative Matrix Factorization Techniques. Signals and Communication Technology. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-48331-2_6
Download citation
DOI: https://doi.org/10.1007/978-3-662-48331-2_6
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-662-48330-5
Online ISBN: 978-3-662-48331-2
eBook Packages: EngineeringEngineering (R0)