OSA's Digital Library

Applied Optics

Applied Optics


  • Vol. 39, Iss. 20 — Jul. 10, 2000
  • pp: 3473–3485

Training of a neural network for image superresolution based on a nonlinear interpolative vector quantizer

Carlos A. Dávila and B. R. Hunt  »View Author Affiliations

Applied Optics, Vol. 39, Issue 20, pp. 3473-3485 (2000)

View Full Text Article

Enhanced HTML    Acrobat PDF (2442 KB)

Browse Journals / Lookup Meetings

Browse by Journal and Year


Lookup Conference Papers

Close Browse Journals / Lookup Meetings

Article Tools



Superresolution is the process of extending the spectrum of a diffraction-limited image beyond the optical passband. We consider the neural-network approach to accomplish superresolution and present results on simulated gray-scale images degraded by diffraction blur and additive noise. Images are assumed to be sampled at the Nyquist rate, which requires spatial interpolation for avoiding aliasing, in addition to frequency-domain extrapolation. A novel, to our knowledge, use of vector quantization for the generation of training data sets is also presented. This is accomplished by training of a nonlinear vector quantizer, whose codebooks are subsequently used in the supervised training of the neural network with backpropagation.

© 2000 Optical Society of America

OCIS Codes
(100.3010) Image processing : Image reconstruction techniques
(100.3020) Image processing : Image reconstruction-restoration
(100.6640) Image processing : Superresolution
(200.4260) Optics in computing : Neural networks

Original Manuscript: May 26, 1999
Revised Manuscript: April 6, 2000
Published: July 10, 2000

Carlos A. Dávila and B. R. Hunt, "Training of a neural network for image superresolution based on a nonlinear interpolative vector quantizer," Appl. Opt. 39, 3473-3485 (2000)

Sort:  Author  |  Year  |  Journal  |  Reset  


  1. C. A. Dávila, B. R. Hunt, “Superresolution of binary images with a nonlinear interpolative neural network,” Appl. Opt. 39, 2291–2299 (2000). [CrossRef]
  2. R. V. Churchill, J. W. Brown, Complex Variables and Applications, 5th ed. (McGraw-Hill, New York, 1990), Chap. 2 and Chap. 12, pp. 324–327.
  3. J. W. Goodman, Introduction to Fourier Optics, 2nd ed. (McGraw-Hill, New York, 1996), Chap. 4, pp. 77–78, and Chap. 6, pp. 137–144, 154–165.
  4. R. W. Gerchberg, “Super-resolution through error energy reduction,” Opt. Acta 21, 709–720 (1974). [CrossRef]
  5. A. Papoulis, “A new algorithm in spectral analysis and band-limited extrapolation,” IEEE Trans. Circuits Syst. 22, 735–742 (1975). [CrossRef]
  6. B. R. Hunt, “Imagery super-resolution: emerging prospects,” in Applications of Digital Image Processing XIV, A. G. Tescher, ed., Proc. SPIE1567, 600–608 (1991). [CrossRef]
  7. W. H. Richardson, “Bayesian-based iterative method of image restoration,” J. Opt. Soc. Am. 62, 55–59 (1972). [CrossRef]
  8. L. B. Lucy, “An iterative technique for the rectification of observed distributions,” Astron. J. 79, 745–754 (1974). [CrossRef]
  9. J. B. Abbiss, B. J. Brames, M. A. Fiddy, “Superresolution algorithms for a modified Hopfield neural network,” IEEE Trans. Signal Process. 39, 1516–1523 (1991). [CrossRef]
  10. D. O. Walsh, P. A. Nielsen-Delaney, “Direct method for superresolution,” J. Opt. Soc. Am. A 11, 572–579 (1994). [CrossRef]
  11. D. E. Rumelhart, G. E. Hinton, R. J. Williams, “Learning internal representations by error propagation,” in Parallel Distributed Processing: Explorations in the Microstructure of Cognition (MIT, Cambridge, Mass., 1986), Vol. 1, pp. 319–362.
  12. S. Haykin, Neural Networks: a Comprehensive Foundation (Macmillan, New York, 1994), Chap. 6.
  13. G. Cybenko, “Approximation by superpositions of a sigmoidal function,” Math. Control Sig. Syst. 2, 303–314 (1989). [CrossRef]
  14. T. Chen, H. Chen, R. Liu, “Approximation capability in C(Rn) by multilayer feedforward networks and related problems,” IEEE Trans. Neural Netw. 6, 25–30 (1995). [CrossRef]
  15. Y. T. Zhou, R. Chellappa, A. Vaid, B. K. Jenkins, “Image restoration using a neural network,” IEEE Trans. Acoust. Speech Signal. Process. 36, 1141–1151 (1988). [CrossRef]
  16. W. Zhang, K. Itoh, J. Tanida, Y. Ichioka, “Hopfield model with multistate neurons and its optoelectronic implementation,” Appl. Opt. 30, 195–200 (1991). [CrossRef] [PubMed]
  17. J. K. Paik, A. K. Katsaggelos, “Image restoration using a modified Hopfield network,” IEEE Trans. Image Process. 1, 49–63 (1992). [CrossRef] [PubMed]
  18. Y. Sun, J. G. Li, S. Y. Yu, “Improvement on performance of modified Hopfield neural network for image restoration,” IEEE Trans. Image Process. 4, 688–692 (1995). [CrossRef] [PubMed]
  19. M. Bilgen, H. S. Hung, “Neural network for restoration of signals blurred by a random, shift-variant impulse response function,” Opt. Eng. 33, 2723–2727 (1994). [CrossRef]
  20. S. W. Perry, L. Guan, “Neural network restoration of images suffering space-variant distortion,” Electron. Lett. 31, 1358–1359 (1995). [CrossRef]
  21. M. Figueiredo, J. Leitão, “Sequential and parallel image restoration: neural network implementations,” IEEE Trans. Image Process. 3, 789–801 (1994). [CrossRef] [PubMed]
  22. K. Sivakumar, U. B. Desai, “Image restoration using a multilayer perceptron with a multilevel sigmoidal function,” IEEE Trans. Signal Process. 41, 2018–2021 (1993). [CrossRef]
  23. B. R. Hunt, “Super-resolution of images: algorithms, principles, performance,” Int. J. Imaging Syst. Technol. 6, 297–304 (1995). [CrossRef]
  24. A. Gersho, “Optimal nonlinear interpolative vector quantization,” IEEE Trans. Commun. 38, 1285–1287 (1990). [CrossRef]
  25. D. G. Sheppard, A. Bilgin, M. S. Nadar, B. R. Hunt, M. W. Marcellin, “A vector quantizer for image restoration,” IEEE Trans. Image Proc. 7, 119–124 (1998). [CrossRef]

Cited By

Alert me when this paper is cited

OSA is able to provide readers links to articles that cite this paper by participating in CrossRef's Cited-By Linking service. CrossRef includes content from more than 3000 publishers and societies. In addition to listing OSA journal articles that cite this paper, citing articles from other participating publishers will also be listed.

« Previous Article  |  Next Article »

OSA is a member of CrossRef.

CrossCheck Deposited