Advertisement

Multimedia Tools and Applications

, Volume 74, Issue 17, pp 6691–6707 | Cite as

Synthetic image super resolution using FeatureMatch

  • S. Avinash Ramakanth
  • R. Venkatesh Babu
Article

Abstract

In this paper, we propose a super resolution (SR) method for synthetic images using FeatureMatch. Existing state-of-the-art super resolution methods are learning based methods, where a pair of low-resolution and high-resolution dictionary pair are trained, and this trained pair is used to replace patches in low-resolution image with appropriate matching patches from the high-resolution dictionary. In this paper, we show that by using Approximate Nearest Neighbour Fields (ANNF), and a common source image, we can by-pass the learning phase, and use a single image for dictionary. Thus, reducing the dictionary from a collection obtained from hundreds of training images, to a single image. We show that by modifying the latest developments in ANNF computation, to suit super resolution, we can perform much faster and more accurate SR than existing techniques. To establish this claim we will compare our algorithm against various state-of-the-art algorithms, and show that we are able to achieve better and faster reconstruction without any training phase.

Keywords

Super resolution PatchMatch Synthetic images Approximate nearest-neighbour field 

Notes

Acknowledgments

This work was supported by Joint Advanced Technology Programme (JATP), Indian Institute of Science, Bangalore, India.

References

  1. 1.
    Barnes C, Shechtman E, Finkelstein A, Goldman DB (2009) PatchMatch: a randomized correspondence algorithm for structural image editing. ACM Trans Graph 28:24:1–24:11CrossRefGoogle Scholar
  2. 2.
    Borman S, Stevenson RL (1998) Super-resolution from image sequences-a review. In: Midwest symposium on circuits and systems, pp 374–378Google Scholar
  3. 3.
    Chang H, Yeung DY, Xiong Y (2004) Super-resolution through neighbor embedding. In: Proceedings of the 2004 IEEE computer society conference on computer vision and pattern recognition, vol 1, pp I–275–I–282Google Scholar
  4. 4.
    Donoho D (2006) Compressed sensing. IEEE Trans Inf Theory 52(4):1289–1306zbMATHMathSciNetCrossRefGoogle Scholar
  5. 5.
    Farsiu S, Robinson MD, Elad M, Milanfar P (2004) Fast and robust multiframe super resolution. IEEE Trans Image Process 13(10):1327–1344CrossRefGoogle Scholar
  6. 6.
    Gao X, Wang Q, Li X, Tao D, Zhang K (2011) Zernike-moment-based image super resolution. Trans Image Process 20(10):2738–2747MathSciNetCrossRefGoogle Scholar
  7. 7.
    Glasner D, Bagon S, Irani M (2009) Super-resolution from a single image. In: International conference on computer visionGoogle Scholar
  8. 8.
    Hou HS, Andrews HC (1978) Cubic splines for image interpolation and digital filtering. IEEE Trans Acoust Speech Signal Processing 26(6):508–517zbMATHCrossRefGoogle Scholar
  9. 9.
    Kim KI, Kwon Y (2010) Single-image super-resolution using sparse regression and natural image prior. IEEE Trans Pattern Anal Machine Intell 32(6):1127–1133MathSciNetCrossRefGoogle Scholar
  10. 10.
    Kim S, Su WY (1993) Recursive high-resolution reconstruction of blurred multiframe images. IEEE Trans Image Process 2(4):534–539CrossRefGoogle Scholar
  11. 11.
    Li X, Hu Y, Gao X, Tao D, Ning B (2010) A multi-frame image super-resolution method. Signal Process 90(2):405–414zbMATHCrossRefGoogle Scholar
  12. 12.
    Li X, Orchard MT (2001) New edge-directed interpolation. IEEE Trans Image Process 10(10):1521–1527Google Scholar
  13. 13.
    Protter M, Elad M, Takeda H, Milanfar P (2009) Generalizing the non-local-means to super-resolution reconstruction. In: IEEE transactions on image processing, p 36Google Scholar
  14. 14.
    Ramakanth SA, Babu RV (2012) FeatureMatch: an efficient low dimensional patchmatch technique. In: Proceedings of the eighth Indian Conference on Computer Vision, Graphics and Image Processing, ICVGIP ’12, pp 45:1–45:7Google Scholar
  15. 15.
    Ramakanth SA, Babu RV (2014) Super resolution using a single image dictionary. In: IEEE international conference on electronics, computing and communication technologiesGoogle Scholar
  16. 16.
    Ramakanth SA, Venkatesh Babu R (2014) FeatureMatch: a general ANNF estimation technique and its applications. IEEE Trans Image Process 23(5):2193-2205Google Scholar
  17. 17.
    Sudarshan S, Babu RV (2012) Super resolution via sparse representation in l 1 framework. In: ICVGIP, pp 77:1–77:7Google Scholar
  18. 18.
    Sun J, Xu Z, Shum HY (2008) Image super-resolution using gradient profile prior. In: IEEE conference on computer vision and pattern recognitionGoogle Scholar
  19. 19.
    Viola PA, Jones MJ (2001) Rapid object detection using a boosted cascade of simple features. In: CVPR (1), pp 511–518Google Scholar
  20. 20.
    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
  21. 21.
    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
  22. 22.
    Yang J, Wright J, Huang TS, Ma Y (2010) Image super-resolution via sparse representation, vol 19Google Scholar
  23. 23.
    Zeyde R, Elad M, Protter M (2010) On single image scale-up using sparse-representations. In: International conference on curves and surfaces, pp 711–730Google Scholar
  24. 24.
    Zhang D, Wu X (2006) An edge-guided image interpolation algorithm via directional filtering and data fusion. IEEE Trans Image Process 15(8):2226–2238CrossRefGoogle Scholar
  25. 25.
    Zhang H, Yang J, Zhang Y, Huang TS (2010) Non-local kernel regression for image and video restoration. In: Europian conference on computer vision, vol 6313. Springer, Berlin Heidelberg, pp 566–579Google Scholar
  26. 26.
    Zhang K, Gao X, Tao D, Li X (2012) Multi-scale dictionary for single image super-resolution. In: Computer Vision and Pattern Recognition, pp 1114–1121Google Scholar

Copyright information

© Springer Science+Business Media New York 2014

Authors and Affiliations

  1. 1.Video Analytics Lab, SERCIndian Institute of ScienceBangaloreIndia

Personalised recommendations