You are here

Counterpropagation neural network detection of visual primitives

Download pdf | Full Screen View

Date Issued:
1990
Abstract/Description:
University of Central Florida College of Engineering Thesis; Psychological testing has shown that there is an early preattentive stage in the human visual system. At this level, simple features and properties of objects known as visual primitives are deteched spatially in parallel by groupings of cells in the visual cortex known as feature maps. In order to study this preattentive stage in a machine vision system, the biologically inspired, highly parallel architecture of the artificial neural network shows great promise. This paper describes how the unique architecture of the counterpropagation neural network was used to simulate the feature maps which detect visual primitives in the human visual system. The results of the research showed that artificial neural networks are able to reproduce the function of the feature maps with accuracy. The counterpropagation network was able to reproduce the feature maps as theorized, however, future research might investigate the abilities of other neural network algorithms in this area. Development of a method for combining the results of feature maps in a simulation of full scale early vision is also a topic for future research that would benefit from the results reported here.
Title: Counterpropagation neural network detection of visual primitives.
27 views
9 downloads
Name(s): Johnson, Cynthia Lynn, Author
Myler, Harley R., Committee Chair
Engineering, Degree Grantor
Type of Resource: text
Date Issued: 1990
Publisher: University of Central Florida
Language(s): English
Abstract/Description: University of Central Florida College of Engineering Thesis; Psychological testing has shown that there is an early preattentive stage in the human visual system. At this level, simple features and properties of objects known as visual primitives are deteched spatially in parallel by groupings of cells in the visual cortex known as feature maps. In order to study this preattentive stage in a machine vision system, the biologically inspired, highly parallel architecture of the artificial neural network shows great promise. This paper describes how the unique architecture of the counterpropagation neural network was used to simulate the feature maps which detect visual primitives in the human visual system. The results of the research showed that artificial neural networks are able to reproduce the function of the feature maps with accuracy. The counterpropagation network was able to reproduce the feature maps as theorized, however, future research might investigate the abilities of other neural network algorithms in this area. Development of a method for combining the results of feature maps in a simulation of full scale early vision is also a topic for future research that would benefit from the results reported here.
Identifier: CFR0008146 (IID), ucf:52942 (fedora)
Note(s): 1990-08-01
M.S.
Computer Engineering
Masters
This record was generated from author submitted information.
Electronically reproduced by the University of Central Florida from a book held in the John C. Hitt Library at the University of Central Florida, Orlando.
Subject(s): Dissertations
Academic -- Engineering
Engineering -- Dissertations
Academic
Persistent Link to This Record: http://purl.flvc.org/ucf/fd/CFR0008146
Restrictions on Access: public
Host Institution: UCF

In Collections