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

Three-dimensional object representation and invariant recognition using continuous distance transform neural

Y H Tseng1, J N Hwang, F H Sheehan

  • 1Dept. of Electr. Eng., Washington Univ., Seattle, WA.

IEEE Transactions on Neural Networks
|January 1, 1997
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 mathematical model on the propagation of tau pathology in neurodegenerative diseases.

Journal of mathematical biology·2024
Same author

A mathematical model demonstrating the role of interstitial fluid flow on the clearance and accumulation of amyloid β in the brain.

Mathematical biosciences·2019
Same author

On the question of adjustment for multiple testing.

International journal of cardiology·2016
Same author

Physiologic determinants of exercise capacity in patients with different types of right-sided regurgitant lesions: Ebstein's malformation with tricuspid regurgitation and repaired tetralogy of Fallot with pulmonary regurgitation.

International journal of cardiology·2015
Same author

A virally inactivated functional growth factor preparation from human platelet concentrates.

Vox sanguinis·2009
Same author

Clinical effectiveness and safety experience with alefacept in the treatment of patients with moderate-to-severe chronic plaque psoriasis in Taiwan: results of an open-label, single-arm, multicentre pilot study.

Journal of the European Academy of Dermatology and Venereology : JEADV·2008
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 presents a novel neural network for 3D object recognition, effectively handling partial views and noise. The continuous distance transform neural network (CDTNN) enables robust 3D object recognition and deformation analysis.

Area of Science:

  • Computer Vision
  • Machine Learning
  • 3D Data Analysis

Background:

  • 3D object recognition is challenging, especially with partial views and noise.
  • Existing methods often require feature extraction, limiting direct 3D data utilization.

Purpose of the Study:

  • To introduce a neural network solution robust to partial object viewing and noise corruption.
  • To enable direct utilization of 3D data without feature extraction for object recognition.

Main Methods:

  • Parametric representation of objects using a continuous distance transform neural network (CDTNN).
  • CDTNN maps 3D coordinates to distances from the object's surface.
  • Mismatch computation and backpropagation for deformation analysis (affine transform).

Related Experiment Videos

Main Results:

  • Demonstrated robustness to partial object viewing and noise.
  • Successfully applied to 3D heart contour delineation.
  • Achieved invariant recognition of 3D rigid-body objects.

Conclusions:

  • The CDTNN provides a powerful method for direct 3D data processing in recognition tasks.
  • The approach effectively handles object deformation and partial visibility.
  • This technique advances 3D object recognition and analysis capabilities.