(17) * << * >> * Russian * English * Content * All Issues

Some image processing algorithms and their implementation based on neural network technology
I.N. Aizenberg
Uzhhorod National University, Ukraine

 PDF,1014 kB

Pages: 134-142.

Full text of article: Russian language.

Abstract:
The article is devoted to the implementation of some original algorithms for image processing on cellular neural networks (CNN) with multivalued and universal neuroelements. The article considers highly effective, the so-called multivalued filters, their application for noise filtering and frequency correction. It also considers algorithms for detecting contours and filtering impulse noise, as well as their implementation on neural networks. The authors investigate the application of neural networks composed of multivalued neural elements for solving problems of image recognition and extrapolation of image orthogonal spectrum to the high-frequency region in order to increase the resolution of the optical system. Key words: image processing, neural networks, complex-valued neurons.

Citation:
Aizenberg IN. Some image processing algorithms and their implementation based on neural network technology. Computer Optics 1997; 17: 134-142.

References:
  1. L.O. Chua and L. Yang, "Cellular neural networks: Theory", IEEE Trans. on Circuits and Systems, vol. 35, pp.1257-1290, 1988.
  2. S.Tan, J.Hao, J.Vandewalle “Cellular neural networks as a model of associative memories”, Proc. of the 1990 IEEE International Workshop on CNN and their applications (CNNA-90), Budapest, pp. 23-26, 1990.
  3. H. Harrer and J.A. Nossek “Discrete-time cellular neural networks”, Int. J. Circuit Theory and Applicat., vol.20, pp. 453-467, 1992.
  4. N.N. Aizenberg, I.N. Aizenberg "Fast converged learning algorithms for multi-level and universal binary neurons and solving of the some image processing problems", Lect. Notes in Computer Science, Ed.-J. Mira, J. Cabestany, vol. 686, Shpringer, pp. 230- 236, 1993.
  5. N.N.Aizenberg, I.N.Aizenberg "CNN-like networks based on multi-valued and universal binary neurons: learning and application to image processing", Proc. of the Third IEEE International Workshop on Cellular Neural Networks and their Applications, Rome, pp.153-158, 1994
  6. C. Rekeczky, T. Roska and A. Ushida “CNN Based Self-Adjusting Nonlinear Filters” Proc. of the Fourth IEEE International Workshop on Cellular Neural Networks and their Applications, Seville, Spain, pp. 309-314, 1996.
  7. Aizenberg I.N. “Multi-valued non-linear filters and their implementation on cellular neural networks”, Frontiers in Artificial Intelligence and Applications, vol. 41 “Advances in Intelligent Systems” (F.C. Morabito - Ed.) IOS Press, Amsterdam-Berlin-OxfordTokyo- Washington DC, 1997, pp. 135-140.
  8. N.N. Aizenberg, I.N. Aizenberg, G.A. Krivosheev "Multi-Valued Neurons: Mathematical model, Networks, Application to Pattern Recognition", Proc. of the 13 Int.Conf. on Pattern Recognition, Vienna, August 25-30, 1996, Track D, IEEE Computer Soc. Press, pp. 185-189, 1996.
  9. Aizenberg NN, Aizenberg IN, Krivosheev GA. Neural networks based on multi-valued neural elements: learning, image processing and recognition. Computer Optics 1995; 14-15(1): 179-186.
  10. S.Jankowski, A.Lozowski, M.Zurada “ComplexValued Multistate Neural Associative Memory”, IEEE Trans. on Neural Networks, vol.7, No 6, November, pp.1491-1496, 1996.
  11. Aizenberg NN, Ivaskiv YL. Multiple-valued threshold logic, Kiev: Naukova Dumka; 1977.
  12. S.Haykin Neural networks. A comprehensive foundation. Macmillan College Publishing Company, New York, 1994.
  13. I.N. Aizenberg “Processing of noisy and smalldetailed gray-scale images using cellular neural networks” Journal of Electronic Imaging, 6(3), 1997, pp. 272- 285.
  14. A.C. Bovik , T.S. Huang, D.C. Mudson A generalization of median filtering using linear combinations of order statistics’, IEEE Trans. Accoust., Speech, Signal Proc. , vol.31, pp.1342-1349, 1983.
  15. Belikova TP. Simulation of the linear filters in the problems of medical diagnostics, in Digital Image and Fields Processing in the Experimental researches. Moscow: Nauka Publisher, 1990, стр. 130-152.
  16. N.N. Aizenberg, I.N. Aizenberg, T.P. Belikova Extraction and localization of important features on gray-scale images: implementation on the CNN Proc. of the Third IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA- 94), Rome, pp. 207-212, 1994.
  17. N. Ahmed, K.R. Rao Orthogonal Transforms for Digital Signal Processing, Springer 1975.

© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: journal@computeroptics.ru ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20