Image Upscaling Using Multiple Dictionaries of Natural Image Patches

  • Pulak Purkait
  • Bhabatosh Chanda
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7726)


We propose a new high-quality up-scaling technique that extends the existing example based super-resolution (SR) framework. Our approach is based on the fundamental idea that a low-resolution (LR) image could be generated from any of the multiple possible high-resolution (HR) images. Therefore it would be more natural to use multiple predictors of HR patch from LR patch instead of single one. In this work we build a generic framework to estimate an HR image from LR one using an adaptive prior (select the predictor locally) based on the local statistics of LR images. We use natural image patch prior as the HR image statistics. We partition the natural images into documents and group them to discover the inherent topics using probabilistic Latent Semantic Analysis (pLSA) and also learn the dual dictionaries of HR and LR image patch pairs for each of the topics using sparse dictionary learning technique. Then for test image we infer locally which topic it corresponds to and then we use the corresponding learned dual dictionary to generate HR image. Experimental results show the effectiveness of our method over existing state-of-art methods.


Sparse Representation Sparse Code Super Resolution Probabilistic Latent Semantic Analysis Bicubic Interpolation 
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.
    Elad, M., Feuer, A.: Restoration of a single super-resolution image from several blurred, noisy and under-sampled measured images. IEEE Trans. Image Process. 6, 1646–1658 (1997)CrossRefGoogle Scholar
  2. 2.
    Elad, M., Datsenko, D.: Example-based regularization deployed to super-resolution reconstruction of a single image. The Comp. J. 52, 15–30 (2009)CrossRefGoogle Scholar
  3. 3.
    Irani, M., Peleg, S.: Improving resolution by image registration. CVGIP: Graph. Models and Image Process. 53, 231–239 (1991)CrossRefGoogle Scholar
  4. 4.
    Purkait, P., Chanda, B.: Super resolution image reconstruction through bregman iteration using morphologic regularization. IEEE Trans. Image Process. 21, 4029–4039 (2012)MathSciNetCrossRefGoogle Scholar
  5. 5.
    Freeman, W.T., Jones, T.R.: Example-based super resolution. IEEE Comp. Graph. and Appl. 22, 56–65 (2002)CrossRefGoogle Scholar
  6. 6.
    Elad, M., Datsenko, D.: Example-based regularization deployed to super-resolution reconstruction of a single image. The Comp. J. 50, 1–16 (2007)Google Scholar
  7. 7.
    Glasner, D., Bagon, S., Irani, M.: Super-resolution from a single image. In: Proceedings of ICCV, pp. 349–356 (2009)Google Scholar
  8. 8.
    Yang, J., Wright, J., Huang, T.S., Ma, Y.: Image super-resolution via sparse representation. IEEE Trans. Image Process. 19, 2861–2873 (2010)MathSciNetCrossRefGoogle Scholar
  9. 9.
    Kim, K.I., Kwon, Y.: Single-image super-resolution using sparse regression and natural image prior. IEEE Trans. Pattern Anal. Mach. Intell. 32, 1127–1133 (2010)MathSciNetCrossRefGoogle Scholar
  10. 10.
    Dong, W., Zhang, L., Shi, G., Wu, X.: Image deblurring and super-resolution by adaptive sparse domain selection and adaptive regularization. IEEE Trans. Image Process. 20, 533–549 (2011)MathSciNetGoogle Scholar
  11. 11.
    Mairal, J., Bach, F., Ponce, J., Sapiro, G.: Online dictionary learning for sparse coding. In: Int. Conf. on Mach. Learn., ICML (2009)Google Scholar
  12. 12.
    Mairal, J., Bach, F., Ponce, J., Sapiro, G.: Online learning for matrix factorization and sparse coding. J. of Mach. Learn. Resrch (JMLR) 11, 19–60 (2010)MathSciNetzbMATHGoogle Scholar
  13. 13.
    Mairal, J., Elad, M., Sapiro, G.: Sparse representation for color image restoration. IEEE Trans. Image Process. 17, 53–69 (2008)MathSciNetCrossRefGoogle Scholar
  14. 14.
    Le Pennec, E., Mallat, S.: Sparse geometric image representations with bandelets. IEEE Trans. Image Process. 14, 423–438 (2005)MathSciNetCrossRefGoogle Scholar
  15. 15.
    Elad, M., Aharon, M.: Image denoising via sparse and redundant representations over learned dictionaries. IEEE Trans. on Acstc., Spch., and Sig. Process. 15, 1013–1027 (2006)MathSciNetGoogle Scholar
  16. 16.
    Mairal, J., Sapiro, G., Elad, M.: Learning multi-scale sparse representations for image and video restoration. SIAM J. on Multiscale Model. and Simuln. (2008)Google Scholar
  17. 17.
    Yang, J., Wang, Z., Lin, Z., Cohen, S., Huang, T.: Coupled dictionary training for image super resolution. IEEE Trans. Image Process. 21, 233–233 (2012)MathSciNetGoogle Scholar
  18. 18.
    Hofmann, T.: Probabilistic latent semantic indexing. In: Proceedings of ACM SIGIR, pp. 50–57 (1999)Google Scholar
  19. 19.
    Sivic, J., Russell, B.C., Efros, A.A., Zisserman, A., Freeman, W.T.: Discovering objects and their location in images. In: Proceedings of ICCV, pp. 3070–3077 (2005)Google Scholar
  20. 20.
    Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In: Proceedings of CVPR, pp. 2169–2178 (2006)Google Scholar
  21. 21.
    Walker, J.S.: Wavelet-Based Image Compression. Sub-chapter of CRC Press book: Transform and Data Compression. A Primer on Wavelets and Their Scientific Applications. University of Wisconsin, Eau Claire (1999)Google Scholar
  22. 22.
    Sun, J., Xu, Z., Shum, H.Y.: Image super-resolution using gradient profile prior. In: Proceedings of CVPR, pp. 1–8 (2008)Google Scholar
  23. 23.
    Freedman, G., Fattal, R.: Image and video upscaling from local self-examples. ACM Trans. Graph. 28, 1–10 (2010)Google Scholar
  24. 24.
    Fattal, R.: Image upsampling via imposed edge statistics. ACM Trans. Graph. 26, 56–65 (2007)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Pulak Purkait
    • 1
  • Bhabatosh Chanda
    • 1
  1. 1.Indian Statistical InstituteKolkataIndia

Personalised recommendations