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 hierarchical multiple-view approach to three-dimensional object recognition.

W C Lin1, F Y Liao, C K Tsao

  • 1Dept. of Electr. Eng. and Comput. Sci., Northwestern Univ., Evanston, IL.

IEEE Transactions on Neural Networks
|January 1, 1991
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

A large chest wall tumour in an asymptomatic 15-year-old girl.

BMJ case reports·2025
Same author

[Application analysis of clinical implementation and educational promotion of allergen testing in the standardization of diagnosis and treatment].

Zhonghua yu fang yi xue za zhi [Chinese journal of preventive medicine]·2025
Same author

[Impact of asthma action plan-based remote joint management model on asthma control in children].

Zhonghua er ke za zhi = Chinese journal of pediatrics·2023
Same author

Effects of dietary supplementation with Taiwanese tea byproducts and probiotics on growth performance, lipid metabolism, and the immune response in red feather native chickens.

Animal bioscience·2020
Same author

Laetiporus sulphureus-fermented wheat bran enhanced the broiler growth performance by improving the intestinal microflora and inflammation status.

Poultry science·2020
Same author

Effects of mushroom waster medium and stalk residues on the growth performance and oxidative status in broilers.

Animal bioscience·2020
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 a hierarchical, coarse-to-fine approach using Hopfield networks for 3D object recognition. It improves surface and vertex correspondence matching in multi-view systems.

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Robotics

Background:

  • 3D object recognition from multiple views presents challenges in surface and vertex correspondence.
  • Existing object-matching schemes can be complex and difficult to parallelize.

Purpose of the Study:

  • To propose a hierarchical, coarse-to-fine approach for solving surface and vertex correspondence problems in 3D object recognition.
  • To develop a more general, compact, and parallelizable solution compared to conventional methods.

Main Methods:

  • A hierarchical search process employing Hopfield networks at each stage.
  • Coarse search: Hopfield network computes surface matching scores to select candidate object models.
  • Fine search: Another Hopfield network performs vertex matching on selected candidates.

Related Experiment Videos

Main Results:

  • The proposed method effectively identifies the best matched 3D object model by combining surface and vertex correspondences.
  • Experimental results using synthetic and real range images validate the proposed approach.
  • The technique offers a solution suitable for parallel implementation.

Conclusions:

  • The hierarchical Hopfield network approach provides an efficient and robust solution for 3D object recognition.
  • This method enhances the accuracy and suitability for parallel processing in multi-view recognition systems.