Share Email Print
cover

Proceedings Paper

The use of global image characteristics for neural network pattern recognitions
Author(s): Maksim O. Kulyas; Oleg L. Kulyas; Aleksey S. Loshkarev
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

The recognition system is observed, where the information is transferred by images of symbols generated by a television camera. For descriptors of objects the coefficients of two-dimensional Fourier transformation generated in a special way. For solution of the task of classification the one-layer neural network trained on reference images is used. Fast learning of a neural network with a single neuron calculation of coefficients is applied.

Paper Details

Date Published: 6 April 2017
PDF: 12 pages
Proc. SPIE 10342, Optical Technologies for Telecommunications 2016, 1034211 (6 April 2017); doi: 10.1117/12.2270475
Show Author Affiliations
Maksim O. Kulyas, Povolzhskiy State Univ. of Telecommunications and Informatics (Russian Federation)
Oleg L. Kulyas, Povolzhskiy State Univ. of Telecommunications and Informatics (Russian Federation)
Aleksey S. Loshkarev, Povolzhskiy State Univ. of Telecommunications and Informatics (Russian Federation)


Published in SPIE Proceedings Vol. 10342:
Optical Technologies for Telecommunications 2016
Vladimir A. Andreev; Anton V. Bourdine; Vladimir A. Burdin; Oleg G. Morozov; Albert H. Sultanov, Editor(s)

© SPIE. Terms of Use
Back to Top
PREMIUM CONTENT
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?
close_icon_gray