Efficient algorithms for space image processing and their realization in cellular neural networks

1Aizenberg, IN
1State Research Institute of Information Infrastructure (Branch), Uzhgorod, Ukraine
Kosm. nauka tehnol. 1998, 4 ;(4):74–84
https://doi.org/10.15407/knit1998.04.074
Section: Space Materials and Technologies
Publication Language: Russian
Abstract: 
Classical cellular neural networks as well as cellular networks of multiple-valued and universal neural elements are considered. A number of original linear filters, their use in noise filtering and frequency correction are described Algorithms for global precise contour allocation and contour allocation in narrow directions are also discussed. All algorithms are realized in cellular neural networks and illustrated by examples of space image processing.
Keywords: cellular neural networks, image processing
References: 
1. Aizenberg I. N. A universal logic element over the complex field. Kibernetika, No.3, 116—121 (1991) [In Russian].
https://doi.org/10.1007/bf01068329
2. Aizenberg N. N., Ivas'kiv Yu. L. Many-valued threshold logic, (Naukova Dumka, Kiev, 1977) [In Russian].
3. Belikova T. P. Simulation of the Linear Filters in the Problems of Medical Diagnostics. In: Digital Image and Fields Processing in the Experimental Researches, 130—152 (Nauka, Moscow, 1990) [In Russian].
4. Aizenberg I. N. Processing of noisy and small-detailed gray­scale images using cellular neural networks. J. Electron. Imaging, 6 (3), 265—280 (1997).
https://doi.org/10.1117/12.269905
5. Aizenberg I. N. Multi-valued non-linear filters and their im­plementation on cellular neural networks. In: Frontiers in artificial intelligence and applications. Vol. 41. Advances in Intelligent Systems, Ed.by F. C. Morabito, 135—140 (IOS Press, Amsterdam-Berlin-Oxford-Tokyo-Washington DC, 1997).
6. Aizenberg I. N., Aizenberg N. N. Universal binary and multi­valued neurons paradigm: conception, learning, applications. Lect. Notes Comput. Sci., Eds J. Mira, R. Moreno-Diaz, J. Cabestauy, 1240, 463—472 (1997).
7. Aizenberg N. N., Aizenberg I. N. CNN Based  on Multi-Valued Neuron as a Model of Associative Memory for Gray-Scale Images. Proc. of the Second IEEE Internal. Workshop on Cellular Neural Networks and their Applications, Technical University Munich, Germany, October 14—16, 1992, 36—41 (1992).
8. Aizenberg N. N., Aizenberg I. N. Fast converged learning algorithms for multi-level and universal binary neurons and solving of the some image processing problems. Lect. Notes Comput. Sci., Eds J. Mira, J. Cabestany, 686, 230—236 (1993).
9. Aizenberg N. N., Aizenberg I. N. CNN-like networks based on multi-valued and universal binary neurons', learning and application to image processing. Proc. of the Third IEEE Internal. Workshop on Cellular Neural Networks and their applications, 153—158 (Rome, 1994).
https://doi.org/10.1109/CNNA.1994.381692
10. Aizenberg N. N., Aizenberg I. N., Belikova T. P. Extraction and localization of important features on gray-scale images: implementation on the CNN. Proc. of the Third IEEE Intern. Workshop on Cellular Neural Networks and their applications (CNNA-94), 207—212 (Rome, 1994).
https://doi.org/10.1109/CNNA.1994.381678
11. Aizenberg N. N., Aizenberg I. N., Krivosheev G. A. Multivalued neurons: learning, networks, application to image recognition and extrapolation of temporal series. Lett Notes Comput. Sci., Eds J. Mira, F. Sandoval, 930, 389—395 (1995).
12. Astola J., Kuosmanen P. Fundamentals of non-linear digital filtering. (CRC Press, New York, 1997).
13. Chua and Yang L. Cellular neural networks: Theory. IEEE Trans. Circuits and Syst., 35, 1257—1290 (1988).
https://doi.org/10.1109/31.7600
14. Harrer H., Nossek J. A. Discrete-time cellular neural networks. Int. J. Circuit Theory and Applications, 20, 453—467 (1992).
https://doi.org/10.1002/cta.4490200503
15. Haykin S. Neural networks. A comprehensive foundation. (Macmillan College Publ. Comp., New York, 1994).
16. Pratt W. K. Digital Image Processing. (John Wiley & Sons, New York, 1978).
17. Rekeczky, Roska T., and Ushida A. CNN Based Self-Adjusting Nonlinear Filters. Proc. of the Fourth IEEE Internat. Workshop on Cellular Neural Networks and their applications, 309—314 (Seville, 1996).
18. Shi B. E. Order-statistic filtering with cellular neural networks. Proc. of the Third IEEE Internat, Workshop on Cellular Neural Networks and their applications, 441—444 (Rome, 1994).
https://doi.org/10.1109/cnna.1994.381635

19. Tan S., Hao J., Vandewalle J. Cellular neural networks as a model of associative memories. Proc. of the 1990 IEEE Internat. Workshop on CNN and their applications (CNNA-90), 23—26 (Budapest, 1990).
https://doi.org/10.1109/cnna.1990.207504