Share Email Print

Proceedings Paper

Optical vortices localization with artificial neural network
Author(s): Wojciech Fraczek; Tomasz Guszkowski
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

This paper presents a new technique of localization of Optical Vortex center (Vortex Point), which is based on Artificial Neural Network. The network accepts as inputs intensities of pixels in a square sub-area of fixed size and produces two output signals correlated to X and Y coordinates of vortex point. A feed-forward neural network with one hidden, non-linear layer was used. The learning criterion was Mean Squared Error and the net was trained with Levenberg-Marquardt algorithm implemented in MATLAB with distorted and noisy images of simulated Optical Vortex Interferometer. The authors provide the results of localization for two sizes of sub-area and two types of simulated interference patterns. The first type of interferogram contain lattice of optical vortices obtained by interference of three plane waves and the second type of interferogram with fringe bifurcations created by interference of lattice of optical vortex with additional, fourth plane wave. The results of simulations suggest possible employment of the proposed method in an experimental setup due to the localization error median being around 0.4 pixel for "three waves" case and 0.9 pixel for "four waves".

Paper Details

Date Published: 14 December 2010
PDF: 7 pages
Proc. SPIE 7746, 17th Slovak-Czech-Polish Optical Conference on Wave and Quantum Aspects of Contemporary Optics, 77460C (14 December 2010); doi: 10.1117/12.881585
Show Author Affiliations
Wojciech Fraczek, Wrocław Univ. of Technology (Poland)
Tomasz Guszkowski, Wrocław Univ. of Technology (Poland)

Published in SPIE Proceedings Vol. 7746:
17th Slovak-Czech-Polish Optical Conference on Wave and Quantum Aspects of Contemporary Optics
Jarmila Müllerová; Dagmar Senderáková; Stanislav Jurečka, Editor(s)

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