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

A self-organizing neural system for learning to recognize textured scenes.

S Grossberg1, J R Williamson

  • 1Department of Cognitive and Neural Systems, Boston University, MA 02215, USA. steve@cns.bu.edu

Vision Research
|May 27, 1999
PubMed
Summary

A novel ARTEX model was developed for textured image classification. This self-organizing system integrates visual cortex processing with cognitive learning for superior texture recognition performance.

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

Association of pre-treatment somatic cell counts with bacteriological cure following diagnosis of intramammary infection.

Research in veterinary science·2022
Same author

Premature Burial.

The Hospital·2018
Same author

Small-Vessel Disease: Diabetic Microangiopathy.

Angiology·2016
Same author

Transfer of reducing equivalents across the mitochondrial membrane. I. Hydrogen transfer mechanisms involved in the reduction of pyruvate to lactate in isolated liver cells.

Biochimica et biophysica acta·2009
Same author

Recent advances in RNA structure determination by NMR.

Current protocols in nucleic acid chemistry·2008
Same author

Thermodynamics and kinetics of central domain assembly.

Cold Spring Harbor symposia on quantitative biology·2003

Area of Science:

  • Computational Neuroscience
  • Computer Vision
  • Artificial Intelligence

Background:

  • The visual cortex processes texture and surface properties.
  • Cognitive models explain how the brain learns visual recognition categories.
  • Existing models struggle with context-sensitive texture analysis.

Purpose of the Study:

  • To develop a self-organizing model, ARTEX, for categorizing and classifying textured image regions.
  • To integrate visual processing (FACADE) with cognitive learning (ART) for enhanced texture recognition.
  • To benchmark ARTEX against existing classification methods.

Main Methods:

  • ARTEX combines the FACADE model for visual feature extraction (texture, brightness) with the ART model for category learning.
  • FACADE uses multi-scale filtering, competition, and diffusive filling-in for context-sensitive scene analysis.

Related Experiment Videos

  • ART incrementally learns categories, uses top-down expectations, and searches memory for novel data classification.

    • Main Results:

    • ARTEX effectively categorizes and classifies textured image regions.
    • The model demonstrates superior performance compared to rule-based, backpropagation, and K-nearest neighbor classifiers.
    • ARTEX shows strong performance on natural textures and synthetic aperture radar (SAR) images.

    Conclusions:

    • ARTEX provides an effective framework for self-organizing texture classification.
    • The integration of visual and cognitive processing enhances recognition capabilities.
    • ARTEX represents a significant advancement in automated texture analysis and image classification.