Skip to content Skip to navigation
University of Warwick
  • Study
  • |
  • Research
  • |
  • Business
  • |
  • Alumni
  • |
  • News
  • |
  • About

University of Warwick
Publications service & WRAP

Highlight your research

  • WRAP
    • Home
    • Search WRAP
    • Browse by Warwick Author
    • Browse WRAP by Year
    • Browse WRAP by Subject
    • Browse WRAP by Department
    • Browse WRAP by Funder
    • Browse Theses by Department
  • Publications Service
    • Home
    • Search Publications Service
    • Browse by Warwick Author
    • Browse Publications service by Year
    • Browse Publications service by Subject
    • Browse Publications service by Department
    • Browse Publications service by Funder
  • Help & Advice
University of Warwick

The Library

  • Login
  • Admin

Seeing things

Tools
- Tools
+ Tools

Wilson, Roland and Knutsson, Hans (1994) Seeing things. University of Warwick. Department of Computer Science. (Department of Computer Science research report). (Unpublished)

[img]
Preview
PDF (Department of Computer Science Research Report)
WRAP_cs-rr-274.pdf - Other - Requires a PDF viewer.

Download (904Kb) | Preview

Request Changes to record.

Abstract

This paper is concerned with the problem of attaching meaningful symbols to aspects of the visible environment in machine and biological vision. It begins with a review of some of the arguments commonly used to support either the 'symbolic' or the 'behaviourist' approach to vision. Having explored these avenues without arriving at a satisfactory conclusion, we then present a novel argument, which starts from the question : given a functional description of a vision system, when could it be said to support a symbolic interpretation? We argue that to attach symbols to a system, its behaviour must exhibit certain well defined regularities in its response to its visual input and these are best described in terms of invariance and equivariance to transformations which act in the world and induce corresponding changes of the vision system state. This approach is illustrated with a brief exploration of the problem of identifying and acquiring visual representations having these symmetry properties, which also highlights the advantages of using an 'active' model of vision.

Item Type: Report
Subjects: Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software
Divisions: Faculty of Science > Computer Science
Library of Congress Subject Headings (LCSH): Computer vision
Series Name: Department of Computer Science research report
Publisher: University of Warwick. Department of Computer Science
Official Date: 10 November 1994
Dates:
DateEvent
10 November 1994Completion
Number: Number 274
Number of Pages: 50
DOI: CS-RR-274
Institution: University of Warwick
Theses Department: Department of Computer Science
Status: Peer Reviewed
Publication Status: Unpublished
Related URLs:
  • Organisation

Request changes or add full text files to a record

Repository staff actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics

twitter

Email us: wrap@warwick.ac.uk
Contact Details
About Us