Abstract
A concept of image recognition is considered on the basis of a combination of signals that are close to the original. A new type of neuron is proposed, which implements an elementary recognition operation. Operation principles of some deterministic neural networks are considered. Examples of identification and classification of signals in the presence of distortions, noises, and interference are given.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Wassermen, F., Neurocomputer Engineering. Translated under the title Neirokomp’yuternaya tekhnika, Moscow: Mir, 1992.
Artificial Neural Networks: Concepts and Theory, IEEE Computer Soc. Press, 1992.
Science and Eudcation. Information on Neural Networks: http://www.91.ru/Education/.
Osovskii, S., Neural Networks for Information Processing, Moscow: Finansy i Statistika, 2004.
Barkhatov, V.A., Recognizing Imperfections with an Artificial Neural Network of a Special Type [Russ. J. Nondestr. Test. (Engl. Transl.), 2006, vol. 42, no. 2, p. 92], Defektoskopiya, 2006, no. 2, pp. 28–39.
Max, J., Methodes et techniques de traitement du signal et application aux mesures physiques, 2 vols., Paris: Masson, 1981. Translated under the title Metody i tekhnika obrabotki signalov pri fizicheskikh izmereniyakh, Moscow: Mir, 1983.
Author information
Authors and Affiliations
Additional information
Original Russian Text © V.A. Barkhatov, 2006, published in Defektoskopiya, 2006, Vol. 42, No. 4, pp. 14–27.
Rights and permissions
About this article
Cite this article
Barkhatov, V.A. Detection of signals and their classification with image-recognition methods. Russ J Nondestruct Test 42, 227–236 (2006). https://doi.org/10.1134/S1061830906040024
Received:
Issue Date:
DOI: https://doi.org/10.1134/S1061830906040024