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

HAVNET: A New Neural Network Architecture for Pattern Recognition.

Ryan G. Rosandich1

  • 1The University of Kansas Regents Center, USA

Neural Networks : the Official Journal of the International Neural Network Society
|January 1, 1997
PubMed
Summary

A novel artificial neural network uses Hausdorff distance for 2D binary pattern recognition, achieving human-like performance. This architecture enhances tasks like character recognition and 3D vision.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same journal

Injecting reasoning into vision-language models via weight-decomposed merging.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

A Non-equilibrium thermodynamic framework for neural networks: A principled correspondence and parameter dynamics.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Dual-pathway mask ranking guided selective fine-tuning for backdoor purification.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Discriminative transfer feature learning for unsupervised domain adaptation.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

ARetinex-Net: Low-light image enhancement with adaptive retinex model and global illumination representation.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

A Multi-Task Learning Framework with Physics Embedded for Signal Reconstruction and State Prediction in Underground Multi-Robot Systems.

Neural networks : the official journal of the International Neural Network Society·2026

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Machine Learning

Background:

  • Current artificial neural networks (ANNs) often lack human-like performance in pattern recognition.
  • Existing similarity metrics in ANNs can be suboptimal for certain tasks.

Purpose of the Study:

  • Introduce a new ANN architecture for 2D binary pattern recognition.
  • Enhance pattern recognition capabilities by employing a novel similarity metric.
  • Improve consistency with human performance in pattern recognition tasks.

Main Methods:

  • Developed a new ANN architecture tailored for 2D binary patterns.
  • Integrated the Hausdorff distance as a unique similarity metric.
  • Presented detailed architecture, learning, and recall equations.

Related Experiment Videos

  • Described an extension for multi-aspect object representation.

    • Main Results:

    • The network demonstrated behavior more consistent with human performance.
    • Achieved very good results on an example pattern recognition task.
    • The multi-aspect extension significantly increased utility for complex tasks.

    Conclusions:

    • The proposed ANN architecture with Hausdorff distance is effective for 2D binary pattern recognition.
    • The network offers improved performance and human-like consistency.
    • The multi-aspect extension broadens its applicability to character recognition and 3D vision.