Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Learning paradigms for image interpretation.

T Caelli1

  • 1Department of Computing Science, The University of Alberta, Edmonton, Canada. tcaelli@ualberta.ca

Spatial Vision
|February 24, 2001
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Object recognition and image understanding: theories of everything?

Spatial vision·2001
Same author

Theory of spatiochromatic image encoding and feature extraction.

Journal of the Optical Society of America. A, Optics, image science, and vision·2000
Same author

The IPRS Image Processing and Pattern Recognition System.

Spatial vision·1997
Same author

A structural and relational approach to handwritten word recognition.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·1997
Same author

Visual learning of patterns and objects.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·1997
Same author

Recognition-by-parts: a computational approach to human learning and generalization of shapes.

Biological cybernetics·1996
Same journal

Comment on 'angle illusion on a picture's surface' by Hammad et al. (2008).

Spatial vision·2009
Same journal

Feature-based attentional modulation increases with stimulus separation in divided-attention tasks.

Spatial vision·2009
Same journal

Spatial distance between target and irrelevant patch modulates detection in a texture segmentation task.

Spatial vision·2009
Same journal

Inhibition related impairments of coherent motion perception in the attention-induced motion blindness paradigm.

Spatial vision·2009
Same journal

Recognition units in reading: backward masking experiments.

Spatial vision·2009
Same journal

Spatial-temporal modeling of interactive image interpretation.

Spatial vision·2009
See all related articles

This paper explores how systems learn and use spatial information for image understanding and object recognition. It emphasizes integrating visual data with existing knowledge for effective recognition beyond simple feature matching.

Area of Science:

  • Computer Vision
  • Cognitive Science
  • Artificial Intelligence

Background:

  • Image understanding and object recognition involve integrating visual perception with prior knowledge.
  • Current approaches often focus on feature extraction and matching, potentially limiting scientific understanding.

Purpose of the Study:

  • To explicate how systems learn and encode spatial information from images.
  • To investigate how this encoded knowledge is matched with new visual data.
  • To question the sufficiency of feature-based methods in image understanding.

Main Methods:

  • Conceptual analysis of image understanding processes.
  • Discussion of knowledge representation and matching mechanisms.
  • Exploration of learning spatial information from visual data.

Related Experiment Videos

Main Results:

  • Highlighting the importance of binding visual input with known information.
  • Demonstrating the necessity of understanding spatial information encoding and retrieval.
  • Challenging the paradigm that image understanding is solely about feature extraction and matching.

Conclusions:

  • Effective image understanding requires a deeper integration of learned knowledge with visual input.
  • Future research should move beyond purely feature-centric models.
  • A comprehensive understanding necessitates exploring how spatial knowledge is acquired, represented, and utilized.