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

Visual shape recognition with contour propagation.

C Rasche1

  • 1Department of Psychology, University of Notre Dame, South Bend, IN, USA. cur12@psu.edu

Biological Cybernetics
|June 10, 2005
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

[Market and competitive positioning of specialized practices: competitive advantages through strategic productivity planning].

Der Urologe. Ausg. A·2011
Same author

[Process-oriented cost calculation in interventional radiology. A case study].

Der Radiologe·2011
Same author

Long-term reduction in local inflammation by a lipid raft molecule in atopic dermatitis.

Allergy·2010
Same author

Smooth pursuit eye movements to isoluminant targets.

Journal of neurophysiology·2008
Same author

Docosahexaenoic acid (DHA) supplementation in atopic eczema: a randomized, double-blind, controlled trial.

The British journal of dermatology·2008
Same author

Forward- and backpropagation in a silicon dendrite.

IEEE transactions on neural networks·2008
Same journal

Harmonic memory in phasor neural networks.

Biological cybernetics·2026
Same journal

Correction: Decreased spinal inhibition leads to undiversified locomotor patterns.

Biological cybernetics·2026
Same journal

Foundational issues of network models in biology.

Biological cybernetics·2026
Same journal

Dynamical mechanisms for coordinating long-term working memory based on the precision of spike-timing in cortical neurons.

Biological cybernetics·2026
Same journal

Distinct dopaminergic spike-timing-dependent plasticity rules are suited to different functional roles.

Biological cybernetics·2026
Same journal

Fluctuation-response relations for a two-stage population of spiking neurons stimulated by common noise.

Biological cybernetics·2026
See all related articles

A novel neural architecture efficiently encodes visual space for superior shape recognition. This method surpasses traditional contour geometry analysis by creating a versatile "shape map".

Area of Science:

  • Computational Neuroscience
  • Computer Vision
  • Artificial Intelligence

Background:

  • Traditional shape recognition relies heavily on contour geometry.
  • Existing methods often struggle with variations in translation, deformation, and scaling.

Purpose of the Study:

  • To introduce a new neural architecture for encoding visual space within and outside shapes.
  • To enhance shape recognition efficiency and robustness.

Main Methods:

  • Propagating shape contours across an excitable neuronal map.
  • Utilizing orientation columns to create a vector field.
  • Encoding this vector field as directional synaptic connections in a 'shape map'.

Main Results:

Related Experiment Videos

  • The developed 'shape map' demonstrates robust identification of its preferred input under transformations (translation, deformation, scaling, fragmentation).
  • The architecture effectively discriminates between different shapes.
  • Encoding visual space proved more efficient than contour geometry alone for recognition tasks.

    • Conclusions:

    • The proposed neural architecture offers a more efficient and robust approach to shape recognition.
    • This method leverages the encoding of visual space, outperforming contour-based methods.
    • The 'shape map' provides a powerful internal representation for complex visual pattern matching.