Single Image Super Resolution Reconstruction in Perturbed Exemplar Sub-space

  • Takashi Shibata
  • Akihiko Iketani
  • Shuji Senda
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7726)


This paper presents a novel single image super resolution method that reconstructs a super resolution image in an exemplar sub-space. The proposed method first synthesizes LR patches by perturbing the image formation model, and stores them in a dictionary. An SR image is generated by replacing the input image patchwise with an HR patch in the dictionary whose LR patch best matches the input. The abundance of the exemplars enables the proposed method to synthesize SR images within the exemplar sub-space. This gives numerous advantages over the previous methods, such as the robustness against noise. Experiments on documents images show the proposed method outperforms previous methods not only in image quality, but also in recognition rate, namely about 30% higher than the previous methods.


Root Mean Square Error Recognition Rate Point Spread Function Document Image Proposed Method 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Baker, S., Kanade, T.: Limits on super-resolution and how to break them. IEEE Trans. Pattern Analysis and Machine Intelligence 24, 1167–1183 (2002)CrossRefGoogle Scholar
  2. 2.
    Datsenko, D., Elad, M.: Example-based single document image super-resolution: a global MAP approach with outlier rejection. Multidimensional Systems and Signal Processing 18, 103–121 (2007)MathSciNetzbMATHCrossRefGoogle Scholar
  3. 3.
    Farsiu, S., Robinson, M.D., Elad, M., Milanfar, P.: Fast and robust multi-frame super-resolution. IEEE Tran. on Image Processing 13, 1327–1344 (2004)CrossRefGoogle Scholar
  4. 4.
    Freeman, W.T., Jones, T.R., Pasztor, E.C.: Example-based super-resolution. IEEE Computer Graphics and Applications 22, 56–65 (2002)CrossRefGoogle Scholar
  5. 5.
    Irani, M., Peleg, S.: Improving resolution by image registration. CVGIP: Graphical Models and Image Processing 53, 231–239 (1991)CrossRefGoogle Scholar
  6. 6.
    Ng, M.K., Shen, H., Lam, E.Y., Zhang, L.: A total variation regularization based super-resolution reconstruction algorithm for digital video. EURASIP Journal on Advances in Signal Processing 74585 (2007)Google Scholar
  7. 7.
    Park, S.C., Park, M.K., Kang, M.G.: Super-resolution image reconstruction: a technical overview. IEEE Signal Processing Magazine 20, 21–36 (2003)CrossRefGoogle Scholar
  8. 8.
    Yang, J., Wright, J., Huang, T., Ma, Y.: Image super-resolution via sparse representation. IEEE Trans. on Image Processing 19, 2861–2873 (2010)MathSciNetCrossRefGoogle Scholar
  9. 9.
    Zeyde, R., Elad, M., Protter, M.: On Single Image Scale-Up Using Sparse-Representations. In: Boissonnat, J.-D., Chenin, P., Cohen, A., Gout, C., Lyche, T., Mazure, M.-L., Schumaker, L. (eds.) Curves and Surfaces 2011. LNCS, vol. 6920, pp. 711–730. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  10. 10.

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Takashi Shibata
    • 1
  • Akihiko Iketani
    • 1
  • Shuji Senda
    • 1
  1. 1.NEC CorporationKawasakiJapan

Personalised recommendations