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 to recognize objects.

W F Bischof1

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

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

This study explores how pattern recognition systems develop rules, apply them to complex scenes, and improve through feedback. It details rule creation, integration of structural information, and performance-based learning for enhanced object recognition.

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

The attentional blink with targets in different spatial locations.

Psychonomic bulletin & review·2002
Same author

Detection of glass patterns by pigeons and humans: implications for differences in higher-level processing.

Psychological science·2001
Same author

Perception of coherent motion in random dot displays by pigeons and humans.

Perception & psychophysics·1999
Same author

Common reference frame for neural coding of translational and rotational optic flow.

Nature·1998
Same author

Bootstrap estimates of the statistical accuracy of thresholds obtained from psychometric functions.

Spatial vision·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 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

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Machine Learning

Background:

  • Pattern recognition systems are crucial for artificial intelligence applications.
  • Developing effective recognition rules is a key challenge in machine learning.
  • Understanding how systems learn and adapt is vital for advancing AI capabilities.

Purpose of the Study:

  • To investigate the development and application of pattern recognition rules.
  • To explore the integration of structural information into recognition systems.
  • To examine methods for improving learned recognition rules through feedback.

Main Methods:

  • Analysis of rule development processes in pattern recognition systems.
  • Examination of rule application to complex pattern recognition, including object recognition in scenes.

Related Experiment Videos

  • Investigation of evidence combination from multiple rules into a unified vector.
  • Study of performance evaluation and feedback mechanisms for rule refinement.

    • Main Results:

    • Recognition rules are developed with embedded structural pattern information.
    • Rules are applied to complex patterns, with evidence combined into a single vector.
    • Performance evaluation and feedback enhance the learning and accuracy of recognition rules.

    Conclusions:

    • Systems can learn and refine pattern recognition rules effectively.
    • Integration of structural information and feedback loops are key to robust recognition.
    • This research contributes to the advancement of intelligent pattern and object recognition systems.