Limited Recurrent Neural Network for Superresolution Image Reconstruction
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.
KeywordsRadial Basis Function Neural Network Bilinear Interpolation Constraint Network Hopfield Neural Network Frequency Domain Approach
Unable to display preview. Download preview PDF.
- 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
- 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.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
- 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