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

Neural computation of inner geometric pattern relations.

H Glünder

    Biological Cybernetics
    |January 1, 1986
    PubMed
    Summary
    This summary is machine-generated.

    This study introduces a novel method for pattern description using geometric relations as features. It explores similarity features and their invariance, proposing a mechanism for extracting relational features from visual representations.

    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

    Imaging on thermoplastic films: a new recording technique for a real-time coherent light valve.

    Applied optics·2010
    Same author

    Synaptic delay learning in pulse-coupled neurons.

    Neural computation·1998
    Same author

    Correlative velocity estimation: visual motion analysis, independent of object form, in arrays of velocity-tuned bilocal detectors.

    Journal of the Optical Society of America. A, Optics and image science·1990
    Same author

    On functional concepts for the explanation of visual pattern recognition.

    Human neurobiology·1986
    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

    Area of Science:

    • Computer Science
    • Artificial Intelligence
    • Pattern Recognition

    Background:

    • Traditional pattern description methods often rely on predefined features.
    • Understanding inner geometric relations is crucial for robust pattern analysis.
    • Early visual representations are heavily influenced by spatial relationships.

    Purpose of the Study:

    • To propose a new method for pattern description based on geometric relations.
    • To investigate the properties of similarity features and their invariance.
    • To present a mechanism for extracting relational features from visual data.

    Main Methods:

    • Utilizing generalized auto comparison functions to define pattern features.
    • Evaluating inner geometric relations for pattern characterization.

    Related Experiment Videos

  • Focusing on similarity features and their invariance properties.
  • Developing a mechanism for extracting relational features from visual representations.

    • Main Results:

    • Demonstrated the effectiveness of geometric relations as pattern features.
    • Highlighted the invariance properties of similarity features under geometric transformations.
    • Proposed a feasible mechanism for extracting relational features.

    Conclusions:

    • Geometric relations offer a powerful approach to pattern description.
    • The proposed method and feature extraction mechanism are promising for visual representation analysis.
    • The study discusses the potential for self-organization in computing structures.