Discussion
A superresolution method based on neural processing of local image representa-
tions has been developed. The method process representation coefficients on local
windows to estimate the HR image values. The dimensionality of input data to this
network is firstly reduced by application of a PCA technique. The eigenimages ob-
tained have been shown to be stable for a wide range of noise levels and image con-
tents, representing intrinsic properties of image structure at sub-pixel levels. Varia-
tions of prediction error with input size have been examined, showing a non-gradual,
structured behavior, reflecting the inadequacy of MSE heuristics in this problem. The
relation of the results with those provided by non-linear methods, such as ICA [12],
will be investigated in future work. The experimental results obtained show the accu-
racy and robustness of the developed method.
Acknowledgments
This work has been partially supported by grants BFI2003-07276 and TIN2004-
04363-C03-03, and by PROFIT project FIT-330100-2004-91.
References
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, n° 6, pp. 996-1011 (1996).
6. C. Miravet and F. B. Rodriguez. “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. Rodriguez. “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, 2° 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, n° 5 (2000).
11. A.Bishop, Neural Networks for Pattern Recognition. Oxford University Press (1995).
12. A. Hyvarinen, J. Karhunen, E. Oja, Independent Component Analysis. Wiley-InterScience
(2001).
More intriguing information
1. Female Empowerment: Impact of a Commitment Savings Product in the Philippines2. Group cooperation, inclusion and disaffected pupils: some responses to informal learning in the music classroom
3. The name is absent
4. Cultural Neuroeconomics of Intertemporal Choice
5. Tax Increment Financing for Optimal Open Space Preservation: an Economic Inquiry
6. The name is absent
7. Short report "About a rare cause of primary hyperparathyroidism"
8. Yield curve analysis
9. CONSUMER ACCEPTANCE OF GENETICALLY MODIFIED FOODS
10. The Structure Performance Hypothesis and The Efficient Structure Performance Hypothesis-Revisited: The Case of Agribusiness Commodity and Food Products Truck Carriers in the South