Cogprints
Login | Create Account

Accurate and robust image superresolution by neural processing of local image representations

Miravet, Carlos and Rodriguez, Francisco B. (2005) Accurate and robust image superresolution by neural processing of local image representations. [Conference Paper]

Full text available as:

[img]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
858Kb

Abstract

Image superresolution involves the processing of an image sequence to generate a still image with higher resolution. Classical approaches, such as bayesian MAP methods, require iterative minimization procedures, with high computational costs. Recently, the authors proposed a method to tackle this problem, based on the use of a hybrid MLP-PNN architecture. In this paper, we present a novel superresolution method, based on an evolution of this concept, to incorporate the use of local image models. A neural processing stage receives as input the value of model coefficients on local windows. The data dimension-ality is firstly reduced by application of PCA. An MLP, trained on synthetic se-quences with various amounts of noise, estimates the high-resolution image data. The effect of varying the dimension of the network input space is exam-ined, showing a complex, structured behavior. Quantitative results are presented showing the accuracy and robustness of the proposed method.

Item Type:Conference Paper
Keywords:superresolution, neural networks, image sequence processing
Subjects:Computer Science > Machine Vision
Computer Science > Neural Nets
ID Code:4567
Deposited By:Miravet, Carlos
Deposited On:20 Oct 2005
Last Modified:12 Sep 2007 18:00

References in Article

Select the SEEK icon to attempt to find the referenced article. If it does not appear to be in cogprints you will be forwarded to the paracite service. Poorly formated references will probably not work.

1. S. Borman, R. Stevenson, “Super-resolution from image sequences-a review”, Midwest Symposium on Circuits and Systems (1998).

2. S. C. Park, M. K. Park, M. G. Kang, “Super-resolution image reconstruction: a technical overview”, IEEE Signal Processing Magazine, 21-35 (2003).

3. R.Y.Tsai and T.S.Huang (Ed.), “Multiframe image restoration and registration”, in Ad-vances in Computer Vision and Image Processing volume 1, pages 317-339, JAI Press Inc.(1984).

4. R. C. Hardie, K. J. Barnard, J. G. Bognar, E. E. Armstrong, and E. A. Watson, "High-resolution image reconstruction from a sequence of rotated and translated frames and its application to an infrared imaging system", Optical Engineering, 37(1), 247-260 (1998).

5. R. R. Schultz and R.L. Stevenson. “Extraction of high-resolution frames from video se-quences”, IEEE Trans. Image Processing, vol. 5, nº 6, pp. 996-1011 (1996).

6. C. Miravet and F. B. Rodríguez, “A hybrid MLP-PNN architecture for fast image super-resolution”, Joint 13th International Conference on Artificial Neural Networks / 10th In-ternational Conference on Neural Information Processing (ICANN/ICONIP), Lecture notes in Computer Science, vol. 2714, Springer-Verlag, pp. 417-424 (2003).

7. C. Miravet and F. B. Rodríguez, “A two-step neural network based algorithm for fast high-resolution image reconstruction”, Image and Vision Computing (submitted).

8. M.Irani, S.Peleg, “Improving resolution by image registration”, CVGIP: Graphical Mod-els and Image Processing. 53, 231-239 (1991).

9. W. Press, S. Teukolsky, W. Vetterling, B. Flannery, Numerical recipes in C, Cambridge University Press, 2º Ed. (1992)

10. M. S. Alam, J. G. Bognar, R. C. Hardie and B. J. Yasuada, “Infrared image registration and high-resolution reconstruction using multiple translationally shifted aliased video frames”, IEEE Transactions on instrumentation and measurement, vol. 49, nº 5 (2000).

11. A.Bishop, Neural Networks for Pattern Recognition. Oxford University Press (1995).

12. A. Hyvärinen, J. Karhunen, E. Oja, Independent Component Analysis. Wiley-InterScience (2001).

Metadata

Repository Staff Only: item control page

Cogprints is powered by EPrints 3 which is developed by the School of Electronics and Computer Science at the University of Southampton. More information and software credits.