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

Using self-organizing maps to learn geometric hash functions for model-based object recognition.

G Bebis1, M Georgiopoulos, N V Lobo

  • 1Department of Computer Science, University of Nevada, Reno, NV 89557, USA.

IEEE Transactions on Neural Networks
|February 7, 2008
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

Surgical practice variation and outcomes regarding single-level posterior approach for degenerative lumbar spondylolisthesis: a Canadian Spine Outcomes Research Network (CSORN) study.

The spine journal : official journal of the North American Spine Society·2025
Same author

An adaptive multiobjective approach to evolving ART architectures.

IEEE transactions on neural networks·2010
Same author

An ordering algorithm for pattern presentation in fuzzy ARTMAP that tends to improve generalization performance.

IEEE transactions on neural networks·2008
Same author

Classification of noisy signals using fuzzy ARTMAP neural networks.

IEEE transactions on neural networks·2008
Same author

Properties of learning of a Fuzzy ART Variant.

Neural networks : the official journal of the International Neural Network Society·2003
Same author

Cross-validation in fuzzy ARTMAP for large databases.

Neural networks : the official journal of the International Neural Network Society·2001
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

This study introduces an elastic hash table using a self-organizing feature map (SOFM) neural network to uniformly distribute geometric hashing invariants, improving data storage and load balancing.

Area of Science:

  • Computer Vision
  • Machine Learning
  • Pattern Recognition

Background:

  • Geometric hashing methods suffer from nonuniform invariant distribution, impacting storage efficiency and parallel processing load balancing.
  • Existing solutions often rely on statistical assumptions and probability theory to achieve uniform invariant distribution.

Purpose of the Study:

  • To propose a novel approach for uniform invariant distribution in geometric hashing using an elastic hash table.
  • To overcome the limitations of traditional methods by adapting to data characteristics through learning.

Main Methods:

  • Associating hash bins with output nodes of a self-organizing feature map (SOFM) neural network.
  • Training the SOFM with invariants to dynamically adjust hash bin locations and sizes based on data density.

Related Experiment Videos

  • Leveraging the SOFM's topology-preserving property for a well-behaved geometric hash function.

    • Main Results:

    • The SOFM-based elastic hash table distributes hash bins proportionally to invariant density, optimizing storage.
    • Hash bins are adjusted in size to hold a near-equal number of invariants, enhancing load balancing.
    • The approach demonstrated strong performance on both artificial and real-world datasets.

    Conclusions:

    • The proposed elastic hash table, utilizing SOFM learning, effectively addresses the nonuniform invariant distribution problem in geometric hashing.
    • This method eliminates the need for prior statistical assumptions about the data, computing the hash function through adaptive learning.
    • The SOFM-based approach offers improved performance and robustness for geometric hashing applications.