Advertisement

Multimedia Tools and Applications

, Volume 75, Issue 21, pp 13107–13120 | Cite as

A novel regularized K-SVD dictionary learning based medical image super-resolution algorithm

  • Jingjing Yang
  • Xiao ZhangEmail author
  • Wei Peng
  • Zhanbiao Liu
Article

Abstract

Recently sparse representations over learned dictionaries have been proven to be a very successful representation method for many image processing applications. In the medical image processing community, image super-resolution has been playing a vital role to make the computer based diagnosis more efficient and accurate. Resolution enhancement through conventional interpolation methods strongly affects the precision of consequent processing steps such as segmentation and registration. In this paper, we propose a novel regularized K-SVD dictionary learning based medical image super-resolution algorithm. First, the dictionary is trained using the modified version of the K-SVD dictionary learning procedure. The sparse coding phase of the K-SVD dictionary learning scheme is then enhanced incorporating a simple and an efficient regularized version of orthogonal matching pursuit. In addition, the dictionary update stage allows for an arbitrary number of atoms at the same time and sparse coefficient vector. In the SR reconstruction procedure, ROMP is adopted to find out for the vector of sparse representation coefficients for the underlying patch. In the final part, mathematical optimization finalizes the SR work effectively. The numerical analysis and experimental simulation prove the feasibility and robustness of our proposed methodology compared with other state-of-the-art algorithms.

Keywords

Medical image super-resolution K-SVD dictionary learning RMOP Sparse presentation Mathematical optimization 

Notes

Acknowledgments

Foundation item: The Major Programs of Hebei North University (No.ZD201301 and No.ZD201302), The Youth Foundation of the Education Department of Hebei Province (No.QN2015225) and Engineering Research Center of Population Health Information, Hebei Province. Authors are grateful to the Hebei North University for financial support to carry out this work.

References

  1. 1.
    Brainweb. BrainWeb: simulated brain database. http://brainweb.bic.mni.mcgill.ca/brainweb/
  2. 2.
    Bruckstein AM, Donoho DL, Elad M (2009) From sparse solutions of systems of equations to sparse modeling of signals and images. SIAM Rev 51(1):34–81MathSciNetCrossRefzbMATHGoogle Scholar
  3. 3.
    Dai W, Xu T, Wang W (2012) Simultaneous codeword optimization (SimCO) for dictionary update and learning. IEEE Trans Signal Process 60(12):6340–6353MathSciNetCrossRefGoogle Scholar
  4. 4.
    Davenport MA, Wakin MB (2010) Analysis of orthogonal matching pursuit using the restricted isometry property. IEEE Trans Inf Theory 56(9):4395–4401MathSciNetCrossRefGoogle Scholar
  5. 5.
    Dong W, Shi G, Zhang L, Wu X (2010) Super-resolution with nonlocal regularized sparse representation. In Visual Communications and Image Processing 2010, pp 77440H–77440H. International Society for Optics and PhotonicsGoogle Scholar
  6. 6.
    Fu C-H, Chen H, Zhang H, Chan Y-L (2014) Single image super resolution based on sparse representation and adaptive dictionary selection. In IEEE 2014 19th International Conference on Digital Signal Processing (DSP), pp 449–453Google Scholar
  7. 7.
    Gill PR, Wang A, Molnar A (2011) The in-crowd algorithm for fast basis pursuit denoising. IEEE Trans Signal Process 59(10):4595–4605MathSciNetCrossRefGoogle Scholar
  8. 8.
    He B, Xu D, Nian R, van Heeswijk M, Yu Q, Miche Y, Lendasse A (2014) Fast face recognition via sparse coding and extreme learning machine. Cogn Comput 6(2):264–277Google Scholar
  9. 9.
    Johnson KA, Becker JA (2013) The whole brain atlas. http://med.harvard.edu/ AANLIB/
  10. 10.
    Liu S, Fu W, Zhao W, Zhou J, Li Q (2013a) A novel fusion method by static and moving facial capture. Math Probl Eng 11(5):497–504Google Scholar
  11. 11.
    Liu S et al (2013b) Fractal property of generalized M-set with rational number exponent. Appl Math Comput 220:668–675Google Scholar
  12. 12.
    Liu S, Fu W, Deng H, Lan C, Zhou J (2013c) Distributional fractal creating algorithm in parallel environment. Int J Distrib Sens Netw 62(2):178–179Google Scholar
  13. 13.
    Liu S, Fu W, He L, Zhou J, Ma M (2014) Distribution of primary additional errors in fractal encoding method. Multimed Tools Appl. doi: 10.1007/s11042-014-2408-1
  14. 14.
    Liu S, Zhang Z, Qi L, Ma M (2015) A fractal image encoding method based on statistical loss used in agricultural image compression. Multimed Tools Appl. doi: 10.1007/s11042-014-2446-8
  15. 15.
    Nazzal M, Ozkaramanli H (2014) Wavelet domain dictionary learning-based single image superresolution. SIViP :1–11Google Scholar
  16. 16.
    Needell D, Vershynin R (2009) Uniform uncertainty principle and signal recovery via regularized orthogonal matching pursuit. Found Comput Math 9(3):317–334MathSciNetCrossRefzbMATHGoogle Scholar
  17. 17.
    Needell D, Vershynin R (2010) Signal recovery from incomplete and inaccurate measurements via regularized orthogonal matching pursuit. IEEE J Sel Top Signal Process 4(2):310–316CrossRefGoogle Scholar
  18. 18.
    Ren J, Liu J, Guo Z (2013) Context-aware sparse decomposition for image denoising and super-resolution. IEEE Trans Image Process 22(4):1456–1469MathSciNetCrossRefGoogle Scholar
  19. 19.
    Rueda A, Malpica N, Romero E (2013) Single-image super-resolution of brain MR images using over-complete dictionaries. Med Image Anal 17(1):113–132CrossRefGoogle Scholar
  20. 20.
    Sajjad M, Mehmood I, Baik SW (2014) Sparse representations-based super-resolution of key-frames extracted from frames-sequences generated by a visual sensor network. Sensors 14(2):3652–3674CrossRefGoogle Scholar
  21. 21.
    Sajjad M, Mehmood I, Baik SW (2015) Image super-resolution using sparse coding over redundant dictionary based on effective image representations. J Vis Commun Image Represent 26:50–65CrossRefGoogle Scholar
  22. 22.
    Seibert M, Kleinsteuber M, Gribonval R, Jenatton R, Bach F (2014) On the sample complexity of sparse dictionary learning. In 2014 I.E. Workshop on Statistical Signal Processing (SSP), pp 244–247Google Scholar
  23. 23.
    Sun J, Xu Z, Shum H-Y (2008) Image super-resolution using gradient profile prior. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2008, pp 1–8Google Scholar
  24. 24.
    Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13(4):600–612CrossRefGoogle Scholar
  25. 25.
    Yang J, Wright J, Huang TS, Ma Y (2010) Image super-resolution via sparse representation. IEEE Trans Image Process 19:2861–2873MathSciNetCrossRefGoogle Scholar
  26. 26.
    Yang J, Wang Z, Lin Z, Cohen S, Huang T (2012) Coupled dictionary training for image super-resolution. IEEE Trans Image Process 21(8):3467–3478MathSciNetCrossRefGoogle Scholar
  27. 27.
    Zhang T (2011) Sparse recovery with orthogonal matching pursuit under RIP. IEEE Trans Inf Theory 57(9):6215–6221MathSciNetCrossRefGoogle Scholar
  28. 28.
    Zhu Q, Wu M, Li J, Deng D (2014) Fabric defect detection via small scale over-complete basis set. Text Res J 84(15):1634–1649CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2015

Authors and Affiliations

  • Jingjing Yang
    • 1
  • Xiao Zhang
    • 1
    Email author
  • Wei Peng
    • 1
  • Zhanbiao Liu
    • 2
  1. 1.School of Information Science and EngineeringHebei North UniversityZhangjiakouChina
  2. 2.The 251ST Hospital of PLAZhangjiakouChina

Personalised recommendations