Neural Network Paradigm for Three-Dimensional Object Recognition

Abstract

Much research has been conducted toward the goal of developing artificial vision systems capable of recognizing three-dimensional objects from two-dimensional images. Such systems would have many applications in an intelligent manufacturing environment. Several systems have been proposed which relyon elaborate geometric or parametric models of objects that must be known a priori. The goal of this research is to develop a vision system that is capable of recognizing objects based on past experience. This paper introduces the highest level of this system, which consists of a neural network that is capable of learning to recognize three-dimensional objects. Knowledge about objects is acquired by learning their various views, guises, or aspects. Learning occurs on two levels. First, supervised competitive learning is employed to teach the network to differentiate between different objects. The competition causes the unique differences between objects to be emphasized in this stage. Second, unsupervised cooperative learning is employed to self-organize the various aspects of a given object. This stage works in a manner similar to the ART family of self-organizing networks. The cooperative learning causes similarities between different aspects of the same object to be emphasized. The object recognition system is intended for use in a manufacturing environment, including tasks such as component identification, classification of visible quality defects, and visual product grading and sorting.

Department(s)

Engineering Management and Systems Engineering

International Standard Serial Number (ISSN)

1996-756X; 0277-786X

Document Type

Article - Conference proceedings

Document Version

Final Version

File Type

text

Language(s)

English

Rights

© 2024 Society of Photo-optical Instrumentation Engineers, All rights reserved.

Publication Date

02 Mar 1994

Link to Full Text

Share

 
COinS