Abstract
In the present paper, the completely innovative architecture of artificial neural network based on Hopfield structure for solving a stereo-matching problem—hybrid neural network, consisting of the classical analog Hopfield neural network and the Maximum Neural Network—is described. The application of this kind of structure as a part of assistive device for visually impaired individuals is considered. The role of the analog Hopfield network is to find the attraction area of the global minimum, whereas Maximum Neural Network is finding accurate location of this minimum. The network presented here is characterized by an extremely high rate of work performance with the same accuracy as a classical Hopfield-like network, which makes it possible to use this kind of structure as a part of systems working in real time. The network considered here underwent experimental tests with the use of real stereo pictures as well as simulated stereo images. This enables error calculation and direct comparison with the classic analog Hopfield neural network as well as other networks proposed in the literature.
Highlights
The use of stereovision is a natural way of determining the distance by the humans
This paper proposes using a novel neural structure based on Hopfield neural network—Hybrid-Maximum Neural Network (HMNN)
The neurons activity map is helpful to the analysis of network work performance. It can be interpreted as a graphical form of fitting matrix to the investigated line—white points mean the neurons with high potentials, and black points correspond to the neurons with low potentials
Summary
The use of stereovision is a natural way of determining the distance by the humans. This idea is not new. – Phase based algorithms based on the Fourier phase information which can be considered as a sort of gradient-based optical flow method, with time derivative approximated by the difference between the left and right Fourier phase images [20,21,22]. This idea became really applicable with the introduction of localized frequency filters called Gabor filters. This one seems to be the most universal, powerful, and developed out of all the above-mentioned methods
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
