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

Transformation and relational-structure schemes for visual pattern recognition. Two models tested experimentally with

D H Foster, R J Mason

    Biological Cybernetics
    |March 6, 1979
    PubMed
    Summary

    A relational-structure model accurately predicts visual pattern recognition, even with pattern rotation. This model, unlike transformation models, shows strong agreement with experimental data, highlighting the importance of inversion invariance in visual processing.

    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

    Achievement of Target Gain Larger than Unity in an Inertial Fusion Experiment.

    Physical review letters·2024
    Same author

    Lawson Criterion for Ignition Exceeded in an Inertial Fusion Experiment.

    Physical review letters·2022
    Same author

    Prophylactic therapy with omeprazole for prevention of equine gastric ulcer syndrome (EGUS) in horses in active training: A meta-analysis.

    Equine veterinary journal·2018
    Same author

    Totally laparoscopic abdominal wall reconstruction: lessons learned and results of a short-term follow-up.

    Hernia : the journal of hernias and abdominal wall surgery·2013
    Same author

    Interaction between rod and cone systems in dichoptic visual masking.

    Neuroscience letters·2009
    Same author

    Obesity should not influence the management of appendicitis.

    Surgical endoscopy·2008

    Area of Science:

    • Cognitive Science
    • Computer Vision
    • Neuroscience

    Background:

    • Visual pattern recognition involves complex processing of visual information.
    • Existing models struggle to account for observed invariances in human visual perception, such as rotation independence.

    Purpose of the Study:

    • To evaluate two computational models of visual pattern recognition against experimental data.
    • To determine which model better explains human performance in recognizing rotated patterns.

    Main Methods:

    • Developed two models: a transformation model and a relational-structure model.
    • Tested models using random-dot patterns rotated at various angles.
    • Compared model predictions with human recognition performance data.

    Related Experiment Videos

    Main Results:

    • The relational-structure model, incorporating pattern inversion invariance, closely matched experimental results across all rotation angles.
    • The transformation model showed poor agreement with experimental data, even with similar invariance properties.

    Conclusions:

    • Relational-structure models provide a better framework for understanding visual pattern recognition than transformation models.
    • Invariance to pattern inversion is a critical factor in explaining human visual recognition performance.