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 neural network architecture for visual selection.

Y Amit1

  • 1Department of Statistics, University of Chicago, IL 60637, USA.

Neural Computation
|July 25, 2000
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

Safety and efficacy of turoctocog alfa (NovoEight®) during surgery in patients with haemophilia A: results from the multinational guardian™ clinical trials.

Haemophilia : the official journal of the World Federation of Hemophilia·2014
Same author

Yttrium synoviorthesis of the elbow joints in persons with haemophilia.

Haemophilia : the official journal of the World Federation of Hemophilia·2004
Same author

Bone allograft in revision total knee replacement.

Cell and tissue banking·2004
Same author

Synoviorthesis with radioactive Yttrium in haemophilia: Israel experience.

Haemophilia : the official journal of the World Federation of Hemophilia·2001
Same author

Attractor networks for shape recognition.

Neural computation·2001
Same author

Narrative group therapy with aging child survivors of the Holocaust.

The Israel journal of psychiatry and related sciences·2001
Same journal

A Model-Free Reinforcement Learning Implementation of Decision Making Under Uncertainty by Sequential Sampling.

Neural computation·2026
Same journal

DROP: Distributional and Regular Optimism and Pessimism for Reinforcement Learning.

Neural computation·2026
Same journal

Hierarchical Active Inference Using Successor Representations.

Neural computation·2026
Same journal

W-Kernel and Its Principal Space for Frequentist Evaluation of Bayesian Estimators.

Neural computation·2026
Same journal

A Hidden Markov Model-Inspired Sequence Classification Method for Hyperdimensional Computing.

Neural computation·2026
Same journal

Sparse Graphical Modeling for Electrophysiological Phase-Based Connectivity Using Circular Statistics.

Neural computation·2026
See all related articles

This study presents a novel parallel neural network for efficient visual selection in images. The architecture uses flexible feature arrangements and a generalized Hough transform for robust object detection with minimal training data.

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Computational Neuroscience

Background:

  • Visual selection and object recognition are fundamental challenges in computer vision.
  • Existing methods often require extensive training data and struggle with variations in object appearance and scale.

Purpose of the Study:

  • To introduce a parallel neural network architecture for efficient and robust visual selection.
  • To develop a model capable of detecting objects across various scales and deformations with invariance.
  • To enable object representation learning with minimal training datasets.

Main Methods:

  • Utilizing a parallel neural network architecture.
  • Representing objects via flexible star-type planar arrangements of local features and oriented edges.

Related Experiment Videos

  • Employing a generalized Hough transform for candidate location detection.
  • Implementing a training strategy that selects stable local features from a predefined pool.

    • Main Results:

    • The architecture achieves efficient and robust visual selection in gray-level images.
    • The generalized Hough transform detects candidate locations across scales and deformations, providing invariance.
    • Training requires only small datasets by selecting stable local features.
    • The parallel design allows Hough transform computation without altering network connections.

    Conclusions:

    • The proposed neural network architecture offers an efficient and robust solution for visual selection.
    • The model demonstrates effective object representation and detection capabilities.
    • The architecture provides insights into visual system mechanisms and can explain experimental findings in visual selection.