Multimedia Tools and Applications

, Volume 78, Issue 5, pp 5169–5180 | Cite as

Image compressive recovery based on dictionary learning from under-sampled measurement

  • Feng Zhao
  • Weijian Si
  • Zheng DouEmail author
  • Qidi Wu


Compressive sensing(CS) has attracted many attentions in recent years, which assumes that the signal can be exactly reconstruction from its only a few measurements when it is sparsity enough under a certain domain. In this paper, we address the image compressive recovery problem. Firstly, a specific adaptive dictionary learning method is adopted to represent the image more sparsely, which learns atoms in dictionary from the under-sampled measurement directly and shows some good performance in adapting to the compressed sensing framework. Secondly, by utilizing the nonlocal self-similarity in image, we also propose a novel nonlocal CS model with multiple regularizations to preserve the details in the reconstruction image, which are seen as the important information to human perception. In addition, to further improve the computational efficiency, an iterative algorithm is developed to solve the proposed model effectively. Extensive experiments on various benchmark images verify that, compared to the existing excellent methods, the proposed model shows superior and competitive performance.


Compressed sensing Image recovery Dictionary learning Nonlocal technique Iterative algorithm 


  1. 1.
    Aharon M, Elad M, Bruckstein AM (2006) The K-SVD: An Algorithm for Designing of Overcomplete Dictionaries for Sparse Representation. IEEE Trans Signal Process 54(11):4311–4322CrossRefGoogle Scholar
  2. 2.
    Candès EJ, Demanet L, Donoho DL et al (2005) Fast Discrete Curvelet Transforms. Multiscale Model Simul 5:861–899MathSciNetCrossRefGoogle Scholar
  3. 3.
    Candès EJ, Romberg J, Tao T (2006) Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information. IEEE Trans Inf Theory 52(2):489–509MathSciNetCrossRefGoogle Scholar
  4. 4.
    Candes EJ, Wakin MB, Boyd SP (2008) Enhancing sparsity by reweighted l1 minimization. J. Fourier Anal. Applicat. 14(5–6):877–905CrossRefGoogle Scholar
  5. 5.
    Charalampidis P, Fragkiadakis AG, Tragos EZ (2015) Rate-Adaptive Compressive Sensing for IoT Applications. IEEE Conference on Vehicular Technology, pp: 1–5Google Scholar
  6. 6.
    Chen G, Yang H, Huang L (2012) Optimizing compressive sensing in the internet of things. Future Wireless Network and Information Systems 143:253–262Google Scholar
  7. 7.
    Daubechies I, Friese MD, Mol CD (2004) An iterative thresholding algorithm for linear inverse problems with a sparsity constraint. Commun. Pure Appl. Math. 57:1413–1457MathSciNetCrossRefGoogle Scholar
  8. 8.
    Dong W, Shi G, Li X et al (2014a) Compressive sensing via nonlocal low-rank regularization. IEEE Trans Image Process 23(8):3618–3632MathSciNetCrossRefGoogle Scholar
  9. 9.
    Dong W, Wu X, Shi G (2014b) Sparsity fine tuning in Wavelet domain with application to compressive image reconstruction. IEEE Trans Image Process 23(12):5249–5262MathSciNetCrossRefGoogle Scholar
  10. 10.
    Egiazarian K, Foi A, Katkovnik V (2007) Compressed sensing image reconstruction via recursive spatially adaptive filtering. IEEE International Conference on Image Processing 1:1549–1552Google Scholar
  11. 11.
    Engan K, Aase SO, Husøy JH (2000) Multi-frame compression Theory and design. EURASIP Signal Processing 80(10):2121–2140CrossRefGoogle Scholar
  12. 12.
    He L, Carin L (2009) Exploiting structure in wavelet-based Bayesian compressive sensing. IEEE Trans Signal Process 57(9):3488–3497MathSciNetCrossRefGoogle Scholar
  13. 13.
    Hitomi Y, Gu J, Gupta M, Mitsunaga T, et al (2011) Video from a single code exposure photograph using a learned overcomplete dictionary.IEEE International Conference Computer Vision. pp. 287–294Google Scholar
  14. 14.
    Li A, Shouno H (2014) Dictionary-based image denoising by Fused Lasso atom selection. Math Probl Eng 2014:1–10zbMATHGoogle Scholar
  15. 15.
    Li A, Chen D, Lin K et al (2016) Joint regularization frameworks with applications to image denoising. Circuits Systems and Signal Processing 35(8):2932–3942CrossRefGoogle Scholar
  16. 16.
    Lustig M, Donoho DL, Santos JM et al (2008) Compressed sensing MRI. IEEE Signal Process. Mag 25(2):72–82CrossRefGoogle Scholar
  17. 17.
    Mairal J, Bach F, Ponce J et al (2009) Non-local sparse models for image restoration. Proc. IEEE Int. Conf. Comput. Vis:2272–2279Google Scholar
  18. 18.
    Shihao Ji D (2009) Dunson, and L. Carin. Multi-task compressive sensing.[J] IEEE trans. Signal Process 57(1):92–106MathSciNetGoogle Scholar
  19. 19.
    Tropp J, Gilbert A (2008) Signal recovery from random measurements via orthogonal matching pursuit. [J]. IEEE Trans Inf Theory 53(12):4655–1666MathSciNetCrossRefGoogle Scholar
  20. 20.
    Xiaobo Q, Hou Y, Lam F et al (2014) Magnetic resonance image reconstruction from undersampled measurements using a patch-based nonlocal operator. Med Image Anal 18(6):843–856CrossRefGoogle Scholar
  21. 21.
    Zhang X, Burger M et al (2010) Bregmanized Nonlocal Regularization for Deconvolution and Sparse Reconstruction. SIAM J Imag Sci 3(3):253–276MathSciNetCrossRefGoogle Scholar
  22. 22.
    Zhang J, Zhao D, Zhao C et al (2012) Image Compressive Sensing Recovery via Collaborative Sparsity. IEEE Journal Emerging Sel Top Circuits Syst 2(3):380–391MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2017

Authors and Affiliations

  1. 1.College of Information and Communication EngineeringHarbin Engineering UniveristyHarbinChina

Personalised recommendations