Home // International Journal On Advances in Networks and Services, volume 12, numbers 1 and 2, 2019 // View article

Object Recognition Using Neural Networks and Complex Reflection Signals

Authors:
Hristomir Yordanov
Irina Topalova

Keywords: Scattering signals; Object identification; Neural Networks

Abstract:
Radar based imaging techniques can be used to collect 3D information about objects, which in turn can be used to identify and measure specific parameters of these objects. Such measurements need to correlate specific radar signals with the object properties. This can be done using neural networks, as they are designed to search for patterns, which are difficult to find using analytic methods. This work presents a neural network based reflection signal processing system for object identification by attempting to identify an object placed in a rectangular waveguide. We extract both the phase and the amplitude of the reflected signal and compare recognition systems using amplitude only and using both phase and amplitude.

Pages: 30 to 35

Copyright: Copyright (c) to authors, 2019. Used with permission.

Publication date: June 30, 2019

Published in: journal

ISSN: 1942-2644