Geodesic
An oscillatory network model with controllable synchronization and neuromorphic dynamical method of information processing
Matematičeskoe modelirovanie, Tome 29 (2017) no. 1, pp. 95-108.

Voir la notice de l'article provenant de la source Math-Net.Ru

Spatially two-dimensional oscillatory neural network model with inhomogeneous modifiable oscillatory coupling has been designed and adaptive dynamical method of brightness image segmentation (reconstruction) based on self-organized cluster synchronization in the oscillatory network has been developed. The method imitates the known dynamical binding phenomenon that is presumably used by a number of brain neural structures during their performance. The oscillatory-network approach demonstrates the following capabilities: 1) high quality segmentation of real grey-level and color images; 2) selective image segmentation (exclusion of unnecessary information); 3) solution of a problem of visual scene segmentation — the problem of successive selection of all spatially separated image fragments of almost equal brightness.
Keywords: oscillatory networks, synchronization, neuromorphic methods of information processing, dynamical binding, vision scene analysis.
Mots-clés : image segmentation 
@article{MM_2017_29_1_a6,
     author = {E. S. Grichuk and M. G. Kuzmina and E. A. Manykin},
     title = {An oscillatory network model with controllable synchronization and neuromorphic dynamical method of information processing},
     journal = {Matemati\v{c}eskoe modelirovanie},
     pages = {95--108},
     publisher = {mathdoc},
     volume = {29},
     number = {1},
     year = {2017},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/MM_2017_29_1_a6/}
}
TY  - JOUR
AU  - E. S. Grichuk
AU  - M. G. Kuzmina
AU  - E. A. Manykin
TI  - An oscillatory network model with controllable synchronization and neuromorphic dynamical method of information processing
JO  - Matematičeskoe modelirovanie
PY  - 2017
SP  - 95
EP  - 108
VL  - 29
IS  - 1
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/MM_2017_29_1_a6/
LA  - ru
ID  - MM_2017_29_1_a6
ER  - 
%0 Journal Article
%A E. S. Grichuk
%A M. G. Kuzmina
%A E. A. Manykin
%T An oscillatory network model with controllable synchronization and neuromorphic dynamical method of information processing
%J Matematičeskoe modelirovanie
%D 2017
%P 95-108
%V 29
%N 1
%I mathdoc
%U http://geodesic.mathdoc.fr/item/MM_2017_29_1_a6/
%G ru
%F MM_2017_29_1_a6
E. S. Grichuk; M. G. Kuzmina; E. A. Manykin. An oscillatory network model with controllable synchronization and neuromorphic dynamical method of information processing. Matematičeskoe modelirovanie, Tome 29 (2017) no. 1, pp. 95-108. http://geodesic.mathdoc.fr/item/MM_2017_29_1_a6/

[1] S. Haykin, Neural networks: A comprehensive foundation, Prentice Hall, 1998, 842 pp.

[2] R. Eckhorn, R. Bauer, W. Jordan, M. Brosch, W. Kruse, M. Munk, H. J. Reitboek, Coherent oscillations: A mechanism of feature linking in the visual cortex?, Biol. Cybern., 60 (1988), 121–130 | DOI

[3] C. M. Gray, W. Singer, “Stimulus-specific neuronal in orientation columns of cat visual cortex”, Proc. Natl. Acad. Sci. USA, 86 (1989), 1698–1702 | DOI

[4] D. L. Wang, D. Terman, “Locally excitatory globally inhibitory oscillator networks”, Neural Networks, 6 (1995), 283–286 | DOI

[5] D. L. Wang, G. J. Brown, “Separation of speech from interaction sounds based on oscillatory correlation”, IEEE Trans. on Neural Networks, 10 (1999), 684–692 | DOI

[6] K. Chen, D. Wang, X. Liu, “Weight adaptation and oscillatory correlation for image segmentation”, IEEE Trans. on NN, 11 (2000), 1106–1126 | DOI

[7] Z. Li, “A neural model of contour integration in the primary visual cortex”, Neur. Comp., 10 (1998), 903–940 | DOI

[8] Z. Li, “Visual segmentation by contextual influences via intra-cortical interactions in the primary visual cortex”, Network: Comp. Neural Syst., 10 (1999), 187–212 | DOI

[9] Z. Li, “Pre-attentive segmentation in the primary visual cortex”, Spatial Vision, 13 (2000), 25–50 | DOI

[10] Z. Li, “Computational design and nonlinear dynamics of a recurrent network model of the primary visual cortex”, Neural Comp., 13:8 (2001), 1749–1780 | DOI | Zbl

[11] A. Labbi, R. Milanese, H. Bosch, “A network of FitzHugh–Nagumo oscillators for object segmentation”, Proc. Int. Symp. On Nonlin. Theory and Appl., NOLTA'97 (1997), 581–589

[12] R. M. Borisyuk, Y. B. Kazanovich, “Oscillatory model of attention-guided object selection and novelty detection”, Neural Networks, 17 (2004), 899–907 | DOI

[13] R. M. Borisyuk, Y. B. Kazanovich, D. Chik, V. Tihanoff, A. Cangelosi, “A neural model of selective attention and object segmentation”, Neural Networks, 22 (2009), 707–715 | DOI

[14] M. G. Kuzmina, E. A. Manykin, I. I. Surina, “Spatially distributed oscillatory networks related to modeling of the brain visual cortex”, Proc. of NOLTA'2000 (Dresden, Germany, 2000), v. 1, 335–338

[15] M. G. Kuzmina, E. A. Manykin, I. I. Surina, “Tunable oscillatory network for visual image segmentation”, Proc. of ICANN'2001 (Vienna, Austria), Lecture Notes in Comp. Sci., 2130, 2001, 1013–1019 | DOI | Zbl

[16] M. G. Kuzmina, E. A. Manykin, I. I. Surina, “Ostsilliatornaia set s samoorganizovannymi dinamicheskimi sviaziami dlia segmentatsii izobrazhenii”, Neirokompiutery, 4 (2004), 34–55

[17] M. G. Kuzmina, E. A. Manykin, I. I. Surina, “Oscillatory network with self-organized dynamical connections for synchronization-based visual image segmentation”, BioSystems, 76 (2004), 43–53 | DOI

[18] E. S. Grichuk, M. G. Kuzmina, E. A. Manykin, “Oscillatory network for synchronization-based adaptive image segmentation”, Proc. of IEEE World Congress on Computational Intelligence, WCCI 2006 (Vancouver, Canada, 2006), 2006, 4529

[19] E. S. Grichuk, M. G. Kuzmina, E. A. Manykin, “Oscillatory network for synchronization-based adaptive image segmentation”, Opt. Mem. Neural Networks, 15 (2006), 57–65

[20] E. S. Grichuk, M. G. Kuzmina, E. A. Manykin, “Vydelenie obieektov v zritelnoi stsene ostsilliatornosetevym metodom”, Trudy Vserossiiskoi n.-t. konf. Neiroinformatika-2009, v. 2, 167–172

[21] E. S. Grichuk, M. G. Kuzmina, E. A. Manykin, “Adaptive image processing via synchronization in self-organizing oscillatory network”, Lecture Notes in Electrical Engineering, 27, eds. N. Mastorakis, V. Mladenov, V. T. Kontargyri, Springer, Berlin, 2009, 103

[22] E. S. Grichuk, M. G. Kuzmina, E. A. Manykin, “Object selection in visual scene via oscillatory network with controllable coupling and self-organized performance”, Opt. Mem. Neural Networks, 20 (2011), 113–119 | DOI

[23] M. Kuzmina, E. Manykin, E. Grichuk, Oscilltory neural networks in problems of parallel information processing, De Gruyter, Berlin–Boston, 2014

[24] D. J. Watts, S. H. Strogatz, “Collective dynamics of “small-world” networks”, Nature, 393 (1998), 440 | DOI

[25] W. K. Pratt, Digital Image Processing, Wiley-Interscience, 2007 | Zbl

[26] E. Sharon, M. Galun, D. Sharon, R. Basri, A. Brandt, “Hierarchy and adaptivity in segmenting visual scenes”, Nature, 442 (2006), 810 | DOI

[27] J. Shi, J. Malik, “Normalized cuts and image segmentation”, IEEE Trans. on Patt. Anal. and Machine Intell., 22:8 (2000), 888 | DOI

[28] R. Raussendorf, H. J. Briegel, “A one-way quantum computer”, Phys. Rev. Lett., 86 (2001), 5188 | DOI

[29] R. Raussendorf, D. E. Browne, H. J. Briegel, Phys. Rev. A, 68 (2003), 022312 | DOI

[30] E. S. Grichuk, M. G. Kuzmina, E. A. Manykin, “Nelineinye sviazannye ostsilliatory i odnonapravlennye kvantovye vychmsleniia”, Trudy Vserossiiskoi n.-t. konf. Neiroinformatika-2010, v. 2, 254–261

[31] E. S. Grichuk, M. G. Kuzmina, E. A. Manykin, “Fotonnye kvantovye vychisleniia i sistemy stokhasticheskikh ostsilliatorov”, Trudy 14 Vserossiiskoi n.-t. konferentsii Neiroinformatika-2012, v. 3, 188–197

[32] W. Singer, “The brain, a complex self-organizing system”, European Review, 17:2 (2009), 321–329 | DOI