Limited Recurrent Neural Network for Superresolution Image Reconstruction

  • Yan Zhang
  • Qing Xu
  • Tao Wang
  • Lei Sun
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4233)


The paper proposes a new method for image resolution enhancement from multiple images using the limited recurrent neural network (LRNN) approach, which is a set of collectively operating feed-forward neural networks. In the limited recurrent networks, information about past outputs is fed back through recurrent connections of output units and mixed with the input nodes flowing into the network input as external input nodes. Thus, experience about past search is utilized, which enables LRNN to be capable of both learning and searching the optimal solution for optimization problems in the solution space. Estimates computed from a low-resolution (LR) simulation image sequence and an actual video film sequence show dramatic visual and quantitative improvements over bilinear interpolation, and equivalent performance to that of the frequency domain approach.


Radial Basis Function Neural Network Bilinear Interpolation Constraint Network Hopfield Neural Network Frequency Domain Approach 
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.
    Park, S.C., Park, M.K., Kang, M.G.: Super-Resolution Image Reconstruction: A Technical Overview. IEEE Signal Processing Magazine 5, 21–36 (2003)CrossRefGoogle Scholar
  2. 2.
    Tsai, R.Y., Huang, T.S.: Multiframe image restoration and registration. In: Huang, T.S. (ed.) Advances in computer vision and image processing, pp. 317–339. JAI Press (1984)Google Scholar
  3. 3.
    Patti, A.J., Sezan, M.I., Tekalp, A.M.: Superresolution Video Reconstruction with Arbitrary Sampling Lattices and Nonzereo Aperture Time. IEEE Trans. Image Processing 8, 1064–(1997)CrossRefGoogle Scholar
  4. 4.
    Schulz, R.R., Stevenson, R.L.: Extraction of High-Resolution Frames from Video Sequences. IEEE Trans. Image Processing 6, 996–1011 (1996)CrossRefGoogle Scholar
  5. 5.
    Abiss, J.B., Brames, B.J., Fiddy, M.A.: Superresolution Algorithms for a Modified Hopfield Neural Network. IEEE Trans. Signal Processing 7, 1516–1523 (1991)CrossRefGoogle Scholar
  6. 6.
    Zhang, L.M., Pan, F.Z.: A New Method of Image Super-Resolution Restoration by Neural Networks. In: Proceedings of the 9th International Conference on Neural Information Processing (ICONIP’OZ), vol. 5, pp. 2414–2418Google Scholar
  7. 7.
    Wang, D.H., Talevski, A., Dillon, T.S.: Edge-Preserving Image Restoration Using Adaptive Components-based Radial Basis Function Neural Networks, 1243–1248 (2003), 0-7803-7898-9/03Google Scholar
  8. 8.
    Salari, E., Zhang, S.: Integrated Recurrent Neural Network for Image Resolution Enhancement from Multiple Image Frames. IEEE Proc. Vis. Image Signal Process 5, 299–305 (2003)CrossRefGoogle Scholar
  9. 9.
    Vartak, A.A., Georgiopoulos, M., Anagnostopoulos, G.C.: On-line Gauss-Newton-based learning for Fully Recurrent Neural Networks. Nonlinear Analysis 63, e867–e876 (2005)Google Scholar
  10. 10.
    Hardie, R.C., Barnard, K.J., Bognar, J.G., Armstrong, E.E., Watson, E.A.: High-resolution Image Reconstruction from a Sequence of Rotated and Translated Frames and its Application to an Infrared Imaging System. Opt. Eng. 1, 247–260 (1998)CrossRefGoogle Scholar
  11. 11.
    Kim, S.P., Bose, N.K., Valenzuela, H.M.: Recursive Reconstruction of High Resolution Image From Noisy Undersampled Multiframes. IEEE Trans. Acoustics. Speech. and Signal Processing 6, 1013–1027 (1990)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Yan Zhang
    • 1
  • Qing Xu
    • 1
  • Tao Wang
    • 1
  • Lei Sun
    • 1
  1. 1.Zhengzhou Institute of Surveying and MappingZhengzhouChina

Personalised recommendations