Using Weightless Neural Networks for Vergence Control in an Artificial Vision System

Karin S Komati,Alberto F De Souza

doi:10.1155/2003/626283

Karin S Komati, Alberto F De Souza

Open Access

https://doi.org/10.1155/2003/626283

Copy DOI

Abstract

This paper presents a methodology we have developed and used to implement an artificial binocular vision system capable of emulating the vergence of eye movements. This methodology involves using weightless neural networks (WNNs) as building blocks of artificial vision systems. Using the proposed methodology, we have designed several architectures of WNN-based artificial vision systems, in which images captured by virtual cameras are used for controlling the position of the ‘foveae’ of these cameras (high-resolution region of the images captured). Our best architecture is able to control the foveae vergence movements with average error of only 3.58 image pixels, which is equivalent to an angular error of approximately 0.629°.

Highlights

Our visual perception of the world is egocentric, ie centred in our perceived position in relation to the environment
The best performing architecture produces vergence movements with average error of only 3.58 image pixels, which is equivalent to an angular error of approximately 0.629°
This paper presents the methodology used to develop a vergence control system for an artificial vision system based on weightless neural networks (WNNs)

Summary

Introduction

Our visual perception of the world is egocentric, ie centred in our perceived position in relation to the environment. If our perception were oculocentric, ie centred in the position of our eyes in relation to the environment, it would be awful, as we would perceive the world to be moving with the movements of our eyes. In an apparent paradox, the visual brain areas that first analyse the attributes of the visual input possess an accurate oculocentric neural organisation (Kandel et al 2000); yet, when moving our eyes, we feel that the exterior world is steady. This shows that human visual perception depends on the image on the retina, and on the knowledge of the position of the eyes, head and body. The oculomotor system influences visual perception, and information regarding its status is important for visual perception of the world (Ebenholtz 2001)

Methods

Results

Discussion

Conclusion