Model-Based Bayesian Compressive Sensing of Non-stationary Images Using a Wavelet-Domain Triplet Markov Fields Model


In this paper, a new model-based Bayesian compressive sensing technique for non-stationary images is proposed. Our algorithm is based on the recently addressed triplet Markov fields (TMF) model. The TMF model is well appropriate for non-stationary image processing, owing to the introduction of a third random field which reflects different non-stationarity of images. Furthermore, TMF can extract the interactions among the neighboring sites of an image in a more complete way than the classic hidden Markov models do. In this paper, the inter-scale dependencies between the wavelet coefficients is exploited explicitly in the proposed TMF model, which results in the wavelet domain TMF model. Our proposed model considers the intra- and inter-scale dependencies and the non-stationarity of images simultaneously. Also, we have developed our proposed algorithm for both Gaussian and non-Gaussian measurement noises, and we have modeled the non-Gaussianity of the noise via Laplace distribution. To approximate the posterior distributions of the hidden variables, we resort to a variational Bayesian expectation–maximization algorithm. Simulation results in both the optical and synthetic aperture radar images show that this model leads to an improvement over state-of-the-art algorithms in terms of the reconstruction error and the structural similarity.

This is a preview of subscription content, log in to check access.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10


  1. 1.

    H. Azami, S. Sanei, K. Mohammadi, H. Hassanpour, A hybrid evolutionary approach to segmentation of non-stationary signals. Elsevier Dig. Signal Process. 23, 1103–1114 (2013).

    MathSciNet  Article  Google Scholar 

  2. 2.

    S.D. Babacan, R. Molina, A.K. Katsaggelos, Bayesian compressive sensing using Laplace priors. IEEE Trans. Image Process. 19(1), 53–63 (2010).

    MathSciNet  Article  MATH  Google Scholar 

  3. 3.

    R.G. Baraniuk, Compressive sensing. IEEE Signal Process. Mag. (2007).

    Article  MATH  Google Scholar 

  4. 4.

    R.G. Baraniuk, V. Cevher, M.F. Duarte et al., Model-based compressive sensing. IEEE Trans. Inf. Theory 56(4), 1982–2001 (2010).

    MathSciNet  Article  MATH  Google Scholar 

  5. 5.

    M.J Beal, Variational Algorithms for approximate Bayesian inference, Ph.D. dissertation, Univ. College of London, London, U.K., 2003

  6. 6.

    M.J. Beal, Z. Ghahramani, The variational Bayesian EM algorithm for incomplete data: with application to scoring graphical model structures. Bayesian Stat. 7, 453–463 (2003)

    MathSciNet  Google Scholar 

  7. 7.

    D. Benboudjema, W. Pieczynski, Unsupervised image segmentation using triplet Markov fields. Elsevier Comput. Vis. Image Understand. 99(3), 476–498 (2005).

    Article  Google Scholar 

  8. 8.

    D. Benboudjema, W. Pieczynski, Unsupervised statistical segmentation of nonstationary images using triplet Markov fields. IEEE Trans. Pattern Anal. Mach. Intell. 29(8), 1367–1378 (2007).

    Article  Google Scholar 

  9. 9.

    T. Blumensath, M. Davis, Gradient pursuits. IEEE Trans. Signal. Proc. 56(6), 2370–2382 (2008).

    MathSciNet  Article  MATH  Google Scholar 

  10. 10.

    E.J. Candes, M.B. Wakin, S. Boyd, Enhancing sparsity by reweighted l1mini-mization. J. Fourier Anal. Appl. 14(5–6), 877–905 (2008)

    MathSciNet  Article  Google Scholar 

  11. 11.

    S. Chen, D.L. Donoho, M.A. Saunders, Atomic decomposition by basis pursuit. SIAM J. Sci. Comput. 43(1), 129–159 (2001).

    MathSciNet  Article  MATH  Google Scholar 

  12. 12.

    W. Chen, F. Li, Y. Peng, 3D-MIMO channel estimation under non-Gaussian noise with unknown PDF. Electronics 8(3), 316 (2019).

    Article  Google Scholar 

  13. 13.

    W. Dai, O. Milenkovic, Subspace pursuit for compressive sensing signal reconstruction. IEEE Trans. Inf. Theory 55(5), 2230–2249 (2009).

    MathSciNet  Article  MATH  Google Scholar 

  14. 14.

    D.L. Donoho, Compressed sensing. IEEE Trans. Inf. Theory 52(4), 1289–1306 (2006).

    MathSciNet  Article  MATH  Google Scholar 

  15. 15.

    D.L. Donoho, Y. Tsaig, I. Drori et al., Sparse solution of underdetermined linear equations by stagewise orthogonal matching pursuit. Stanford Stat. Tech. Rep. (2006).

    Article  MATH  Google Scholar 

  16. 16.

    Z. Dou, C. Shi, Y. Lin, W. Li, Modeling of non-Gaussian colored noise and application in CR multi-sensor networks. EURASIP J. Wirel. Commun. Netw. (2017).

    Article  Google Scholar 

  17. 17.

    A. Drémeau, C. Herzet, L. Daudet, Boltzmann machine and mean-field approximation for structured sparse decompositions. IEEE Trans. Signal Process. 60(7), 3425–3438 (2012).

    MathSciNet  Article  MATH  Google Scholar 

  18. 18.

    C. Fvotte, B. Torrsani, L. Daudet et al., Sparse linear regression with structured priors and application to denoising of musical audio. IEEE Trans. Audio Speech Lang. Process. 16(1), 174–185 (2008).

    Article  Google Scholar 

  19. 19.

    V. Filipovic, N. Nedic, V. Stojanovic, Robust identification of pneumatic servo actuators in the real situations. Forsch. Ingenieurwes. 75, 183–196 (2011).

    Article  Google Scholar 

  20. 20.

    I.F. Gorodnitsky, B.D. Rao, Sparse signal reconstruction from limited data using FOCUSS: a re-weighted minimum norm algorithm. IEEE Trans. Signal Process. 43(3), 600–616 (1997).

    Article  Google Scholar 

  21. 21.

    L. He, L. Carin, Exploiting structure in wavelet-based Bayesian compressive sensing. IEEE Trans. Signal Process. 57(9), 3488–3497 (2009).

    MathSciNet  Article  MATH  Google Scholar 

  22. 22.

    L. He, H. Chen, L. Carin, Tree-structured compressive sensing with variational Bayesian analysis. IEEE Signal Process. Lett. 17(3), 233–236 (2010).

    Article  Google Scholar 

  23. 23.

    Ch. Hegde, P. Indyk, L. Schmidt, Approximation algorithms for model-based compressive sensing. IEEE Trans. Inf. Theory 61(9), 5129–5147 (2015).

    MathSciNet  Article  MATH  Google Scholar 

  24. 24.

    X. Hou, L. Zhang, Ch. Gong et al., SAR image Bayesian compressive sensing exploiting the interscale and intrascale dependencies in directional lifting wavelet transform domain. Neurocomputing 133, 358–368 (2014).

    Article  Google Scholar 

  25. 25.

    Sh. Ji, Y. Xue, L. Carin, Bayesian compressive sensing. IEEE Trans. Signal Process. 56(6), 2346–2356 (2008).

    MathSciNet  Article  MATH  Google Scholar 

  26. 26.

    M.I. Jordan, Graphical models. Stat. Sci. 19(1), 140–155 (2004)

    MathSciNet  Article  Google Scholar 

  27. 27.

    M. Karimzadeh, A.M. Rabiei, A. Olfat, Soft-limited polarity-coincidence-array spectrum sensing in the presence of non-Gaussian noise. IEEE Trans. Veh. Technol. 66(2), 1418–1427 (2017).

    Article  Google Scholar 

  28. 28.

    S.Z. Li, Mathematical MRF models, in Markov Random Field Modelling in Image Analysis, ed. by S.Z. Li (Springer, London, 2009), pp. 21–48

    Google Scholar 

  29. 29.

    X. Lian, Y. Wu, W. Zhao et al., Unsupervised SAR image segmentation based on conditional triplet Markov fields. IEEE Geosc. Remote Sens. Lett. 11(7), 1185–1189 (2014).

    Article  Google Scholar 

  30. 30.

    G. Liu, M. Li, Y. Wu, P. Zhang, L. Jia, H. Liu, PolSAR image classification based on Wishart TMF with specific auxiliary field. IEEE Geosci. Remote Sens. Lett. 11(7), 1230–1234 (2014).

    Article  Google Scholar 

  31. 31.

    Sh. Liu, H. Wu, Y. Huang, Y. Yang, J. Jia, Accelerated structure-aware sparse Bayesian learning for 3D electrical impedance tomography. IEEE Trans. Ind. Inform. 15(9), 5033–5041 (2019).

    Article  Google Scholar 

  32. 32.

    Sh. Liu, Y.D. Zhang, T. Shan, R. Tao, Structure-aware Bayesian compressive sensing for frequency-hopping spectrum estimation with missing observations. IEEE Trans. Sig. Process. 66(8), 2153–2166 (2018).

    MathSciNet  Article  MATH  Google Scholar 

  33. 33.

    S. Mallat, Wavelet packet and local cosine bases, in A Wavelet Tour of Signal Processing, 2nd edn., ed. by S. Mallat (Academic Press, New York, 1998), pp. 431–500

    Google Scholar 

  34. 34.

    D. Needell, J.A. Tropp, CoSaMP: iterative signal recovery from incomplete and inaccurate samples. Elsevier App. Comput. Harmon. Anal. 26, 301–321 (2009).

    MathSciNet  Article  MATH  Google Scholar 

  35. 35.

    T. Peleg, Y.C. Eldar, M. Elad, Exploiting statistical dependencies in sparse representations for signal recovery. IEEE Trans. Signal Process. 60(5), 2286–2303 (2012).

    MathSciNet  Article  MATH  Google Scholar 

  36. 36.

    Z. Sadeghigol, M.H. Kahaei, F. Haddadi, Generalized beta Bayesian compressive sensing model for signal reconstruction. Elsevier Dig. Signal Process. 60, 163–171 (2016).

    Article  Google Scholar 

  37. 37.

    Z. Sadeghigol, M.H. Kahaei, F. Haddadi, Model based variational Bayesian compressive sensing using heavy tailed sparse prior. Elsevier Signal Process.: Image Commun. 41, 158–167 (2016).

    Article  Google Scholar 

  38. 38.

    V. Stojanovic, V. Filipovic, Adaptive input design for identification of output error model with constrained output. Circuits Syst. Signal Process. 33, 97–113 (2014).

    MathSciNet  Article  Google Scholar 

  39. 39.

    V. Stojanovic, N. Nedic, Identification of time-varying OE models in presence of non-Gaussian noise: application to pneumatic servo drives. Int. J. Robust Nonlinear Control (2016).

    MathSciNet  Article  MATH  Google Scholar 

  40. 40.

    V. Stojanovic, N. Nedic, Joint state and parameter robust estimation of stochastic nonlinear systems. Int. J. Robust Nonlinear Control (2015).

    Article  MATH  Google Scholar 

  41. 41.

    F. Tan, X. Song, C. Leung, J. Cheng, Collaborative spectrum sensing in a cognitive radio system with Laplacian noise. IEEE Commun. Lett. 16(10), 1691–1694 (2012).

    Article  Google Scholar 

  42. 42.

    R. Torkamani-, R.A. Sadeghzadeh, Bayesian compressive sensing using wavelet based Markov random fields. Signal Process. Image Commun. 58, 65–72 (2017).

    Article  Google Scholar 

  43. 43.

    A. Tropp, A.C. Gilbert, Signal recovery from random measurements via orthogonal matching pursuit. IEEE Trans. Inform. Theory 53(12), 4655–4666 (2007).

    MathSciNet  Article  MATH  Google Scholar 

  44. 44.

    B. Wang, Y.D. Zhang, W. Wang, Robust group compressive sensing for DOA estimation with partially distorted observations. EURASIP J. Adv. Sig. Process. (2016).

    Article  Google Scholar 

  45. 45.

    F. Wang, Y. Wu, Q. Zhang et al., Unsupervised SAR image segmentation using higher order neighborhood-based triplet Markov fields model. IEEE Trans. Geosc. Remote Sens. 52(8), 5193–5205 (2014).

    Article  Google Scholar 

  46. 46.

    L. Wang, L. Zhao, G. Bi et al., Enhanced ISAR imaging by exploiting the continuity of the target scene. IEEE Trans. Geosci. Remote Sens. 52(9), 5736–5750 (2014).

    Article  Google Scholar 

  47. 47.

    L. Wang, L. Zhao, G. Bi et al., Sparse representation-based ISAR imaging using Markov random fields. IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens. 8(8), 3941–3953 (2015).

    Article  Google Scholar 

  48. 48.

    Z. Wong, A.C. Bovik, H.R. Sheikh et al., Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004).

    Article  Google Scholar 

  49. 49.

    Q. Wu, Y.D. Zhang, M.G. Amin et al., Multi-task Bayesian compressive sensing exploiting intra-task dependency. IEEE Signal Process. Lett. 22(4), 430–434 (2015).

    Article  Google Scholar 

  50. 50.

    Y. Wua, P. Zhang, M. Li et al., SAR image multiclass segmentation using a multiscale and multidirection triplet Markov fields model in nonsubsampled contourlet transform domain. Elsevier Inf. Fusion 14(4), 441–449 (2013).

    Article  Google Scholar 

  51. 51.

    Ch. Ye, G. Gui, L. Xu, Compressive sensing signal reconstruction using l0-norm normalized least mean fourth algorithms. Circuits Syst. Signal Process. 37(4), 1724–1752 (2018).

    MathSciNet  Article  Google Scholar 

  52. 52.

    L. Yu, H. Sun, J.P. Barbot et al., Bayesian compressive sensing for cluster structured sparse signals. Elsevier Signal Process. 92, 259–269 (2011).

    Article  Google Scholar 

  53. 53.

    L. Yu, Ch. Wei, J. Jia et al., Compressive sensing for cluster structured sparse signals- variational Bayes approach. IET Signal Process. 10(7), 770–779 (2016).

    Article  Google Scholar 

  54. 54.

    J. Zhang, The mean field theory in EM procedures for Markov random fields. IEEE Trans. Signal Process. 40(10), 2570–2583 (1992).

    Article  MATH  Google Scholar 

  55. 55.

    P. Zhang, M. Li, Y. Wu et al., Unsupervised multi-class segmentation of SAR images using fuzzy triplet Markov fields model. Elsevier Pattern Recog. 45(11), 4018–4033 (2012).

    Article  MATH  Google Scholar 

  56. 56.

    X. Zhao, F. Li, Sparse Bayesian compressed spectrum sensing under Gaussian mixture noise. IEEE Trans. Veh. Technol. 67(7), 6087–6097 (2018).

    Article  Google Scholar 

  57. 57.

  58. 58.

  59. 59.

  60. 60.

  61. 61.

Download references

Author information



Corresponding author

Correspondence to Razieh Torkamani.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Electronic supplementary material

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Torkamani, R., Sadeghzadeh, R. Model-Based Bayesian Compressive Sensing of Non-stationary Images Using a Wavelet-Domain Triplet Markov Fields Model. Circuits Syst Signal Process (2020).

Download citation


  • Bayesian compressive sensing
  • Triplet Markov fields
  • Non-stationary image modeling
  • Wavelet-tree structure
  • Laplacian noise
  • Variational Bayesian expectation maximization