Conclusion
The suggested mechanism of competition between categorical neurons has the following advantages over alternative mechanisms:
-
--it resolves complex images into composing reference images without learning all combinations of the reference images;
-
--it is consistent with the neurophysiological findings of a contribution of intercalary neurons to inhibitory feedback chains;
-
--it requires less RAM volume to store feedback weighting factors, this being particularly important for computer modeling.
We would like to thank Yu. N. Zolotukhin for patient and consistent support of this research.
Similar content being viewed by others
Literature cited
A. Carpenter and S. Grossberg, Comput. Vision, Graphics Image Proces.,37, No. 1, 54–115 (1987).
A. Carpenter and S. Grossberg, Appl. Optics,26, No. 23, 4919–4930 (1987).
S. Grossberg, SIAM-AMS Proc.,13, No. 1, 107–156 (1981).
T. Kohonen, Computer,21, No. 3, 11–24 (1988).
Additional information
Institute for Medical and Biological Cybernetics, Siberian Division of Russian Academy of Medical Sciences, Novosibirsk. Translated from Meditsinskaya Tekhnika, No. 4, pp. 5–9, July–August, 1995.
Rights and permissions
About this article
Cite this article
Tret'yakov, V.P., Mikhailov, S.G. A neural network algorithm for complex binary image recognition requiring no presegmentation. Biomed Eng 29, 171–176 (1995). https://doi.org/10.1007/BF00558868
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF00558868