Nothing Special   »   [go: up one dir, main page]
Skip to main content
Springer Nature Link
Log in

Super-resolution using neural networks based on the optimal recovery theory

  • Published:
Journal of Computational Electronics Aims and scope Submit manuscript

Abstract

An optimal recovery based neural-network Super Resolution algorithm is developed. The proposed method is computationally less expensive and outputs images with high subjective quality, compared with previous neural-network or optimal recovery algorithms. It is evaluated on classical SR test images with both generic and specialized training sets, and compared with other state-of-the-art methods. Results show that our algorithm is among the state-of-the-art, both in quality and efficiency.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Park, S.C., Park, M.K., Kang, M.G.: Super-resolution image reconstruction: a technical overview. IEEE Signal Proc. Mag. 20(3), 21–36 (2003)

    Article  Google Scholar 

  2. Baker, S., Kanade, T.: Limits on super-resolution and how to break them. IEEE Trans. Patt. Anal. Mach. Intell. 24(9), 1167–1183 (2002)

    Article  Google Scholar 

  3. Farsiu, S., Robinson, D., Elad, M., Milanfar, P.: Advances and challenges in super-resolution. Int. J. Imag. Sys. Technol. 14(2), 47–57 (2004)

    Article  Google Scholar 

  4. Freeman, W.T., Pasztor, E.C., Carmichael, O.T.: Learning low-level vision. Int. J. Comp. Vis. 40(1), 25–47 (2000)

    Article  MATH  Google Scholar 

  5. Qiu, G.: Inter-resolution look-up table for improved spatial magnification of images. J. Vis. Commun. Image Represent. 11, 360–373 (2000)

    Article  Google Scholar 

  6. Freeman, W.T., Jones, T.R., Pasztor, E.C.: Example-based super-resolution. IEEE Comp. Graph. Appl. 22(2), 56–65 (2002)

    Article  Google Scholar 

  7. Freeman, W.T., Pasztor, E.C.: Learning to estimate scenes from images. In: Proceedings of the 1998 Conference on Advances in Neural Information Processing Systems II, pp. 775–781 (1998)

  8. Sun, J., Zheng, N., Tao, H., Shum, H.: Image hallucination with primal sketch priors. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, vol. II, pp. 729–736 (2003)

  9. Freeman, W.T., Pasztor, E.C.: Markov networks for super-resolution. In: Proceedings of the 34th Annual Conference on Information Sciences and Systems (2000)

  10. Hertzmann, A., Jacobs, C.E., Oliver, N., Curless, B., Salesin, D.H.: Image Analogies. In: Proceedings of SIGGRAPH 2001, pp. 327–340 (2001)

  11. Chang, H., Yeung, D.Y., Xiong, Y.: Super-resolution through neighbor embedding. In: Proceedings of the IEEE International Conference on Computer Vision, vol. I, pp. 275–282 (2004)

  12. Keys, R.G.: Cubic convolution interpolation for digital image processing. IEEE Trans. Acous., Speech and Signal Proc 29, 1153–1160 (1981)

    Article  MATH  MathSciNet  Google Scholar 

  13. Ramstad, T., Wang, Y., Mitra, S.K.: An efficient image interpolation scheme using hybrid IIR Nyquist filters. Opt. Eng. 31, 1277–1283 (1992)

    Article  Google Scholar 

  14. Chan, A.K., Chui, C.K., Zha, J., Liu, Q.: Local cardinal spline interpolation and its application to image processing. In: Proceedings of the Conference on Curves and Surfaces in Computer Vision and Graphics II, SPIE Proceedings, vol. 1610, pp. 272–283 (1991)

  15. Unser, M., Aldroubi, A., Eden, M.: B-spline signal processing: part I-theory. IEEE Trans. Sign. Proc. 41, 821–833 (1993)

    Article  MATH  Google Scholar 

  16. Unser, M., Aldroubi, A., Eden, M.: B-spline signal processing: part II-efficient design and applications. IEEE Trans. Sign. Proc. 41, 834–848 (1993)

    Article  MATH  Google Scholar 

  17. Thurnhofer, S., Mitra, S.: Edge-enhanced image zooming. Opt. Eng. 35(7), 1862–1870 (1996)

    Article  Google Scholar 

  18. Li, X., Orchard, M.T.: New edge-directed interpolation. IEEE Trans. Image Proc. 10(10), 1521–1527 (2001)

    Article  Google Scholar 

  19. Chan, S.C., Ho, K.L., Kok, C.W.: Interpolation of 2-D signal by subsequence FFT. IEEE Trans. Circuits Sys. Part II 40, 115–118 (1993)

    Article  MATH  Google Scholar 

  20. Kim, S.P., Su, W.: Direct image resampling using block transform coefficients. Sign. Proc.: Image Commun. 5, 259–272 (1993)

    Article  Google Scholar 

  21. Stasinski, R., Konrad, J.: POCS-based image reconstruction from irregularly-spaced samples. In: Proceedings of the 7th IEEE International Conference on Image Processing Vol. 2, pp. 315–318 (2000)

  22. Stasinski, R., Konrad, J.: Improved POCS-based image reconstruction from irregularly-spaced samples. In: Proceedings of the 7th European Signal Processing Conference, Vol. 2 pp. 461–464 (2002)

  23. Chen, G., de Figueiredo, R.J.P.: A unified approach to optimal image interpolation problems based on linear partial differential equation models. IEEE Trans. Image Proc. 2, 41–49 (1993)

    Article  Google Scholar 

  24. Karayiannis, N.B., Venetsanopoulos, A.N.: Image interpolation based on variational principles. Sign. Proc. 25, 259–288 (1991)

    Article  MATH  Google Scholar 

  25. Muresan, D.D., Parks, T.W.: Optimal recovery approach to image interpolation. In: Proceedings of the 8th IEEE International Conference on Image Processing, vol. III, pp. 7–10 (2001)

  26. Shenoy, R.G., Parks, T.W.: An optimal recovery approach to interpolation. IEEE Trans. Sign. Proc. 40(8), 1987–1996 (1992)

    Article  MATH  Google Scholar 

  27. Muresan, D.D., Parks, T.W.: Adaptively quadratic (AQua) image interpolation. IEEE Trans. Image Proc. 13(5), 690–698 (2004)

    Article  Google Scholar 

  28. Muresan, D.D., Parks, T.W.: Demosaicing using optimal recovery. IEEE Trans. Image Proc. 14(2), 267–278 (2005)

    Article  Google Scholar 

  29. Swanston, D.J., Bishop, J.M., Mitchell, R.J.: simple adaptive momentum: New algorithm for training multilayer perceptrons. Elect. Lett. 30, 1498–1500 (1994)

    Article  Google Scholar 

  30. Scalero, R.S., Tepedelenlioglu, N.: A fast new algorithm for training feedforward neural networks. IEEE Trans. Sign. Proc. 40, 203–210 (1992)

    Google Scholar 

  31. Plaziac, N.: Image interpolation using neural networks. IEEE Trans. Image Proc. 8, 1647–1651 (1999)

    Article  Google Scholar 

  32. Go, J., Sohn, K., Lee, C.: Interpolation using neural networks for digital still cameras. IEEE Trans. Consum. Elect. 46(3), 610–616 (2000)

    Article  Google Scholar 

  33. Tsai, R.Y., Huang, T.S.: Multiframe image restoration and registration. Adv. Comp. Vis. Image Proc. 1, 317–339 (1984)

    Google Scholar 

  34. Anderws, H.C., Hunt, B.R.: Digital Image Restoration. Prentice-Hall NJ, (1977)

    Google Scholar 

  35. Moller, A.F.: A scaled conjugate gradient algorithm for fast supervised learning. Neural Networks 6(4), 525–533 (1993)

    Article  Google Scholar 

  36. Michelli, C.A., Rivlin, T.J.: Optimal Estimation in Approximation Theory, Plenum NY, (1976)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science and Engineering, School of Electronics Information & Electric Engineering, Shanghai Jiaotong University, 800 Dongchuan Road,Minhang District, Shanghai, 200240, PR China

    Yizhen Huang & Yangjing Long

  2. Department of Mathematics,Digital Media and Data Reconstruction Lab., Shanghai Jiaotong University, 800 Dongchuan Road,Minhang District, Shanghai, 200240, PR China

    Yangjing Long

Authors
  1. Yizhen Huang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yangjing Long
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yizhen Huang.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Huang, Y., Long, Y. Super-resolution using neural networks based on the optimal recovery theory. J Comput Electron 5, 275–281 (2006). https://doi.org/10.1007/s10825-006-0145-z

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10825-006-0145-z

Keywords

Search

Navigation