Jove
Visualize
Contact Us

Related Experiment Videos

Invariant object recognition using higher-order neural networks, line-segment spectra and multi-resolution training

M F Augusteijn1, M C Winterbottom

  • 1Department of Computer Science, University of Colorado at Colorado Springs 80933-7150, USA. mfa@antero.uccs.edu

International Journal of Neural Systems
|June 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

Radical pruning: a method to construct skeleton radial basis function networks.

International journal of neural systemsยท2000
See all related articles
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

A novel second-order neural network architecture enables invariant object recognition without combinatorial network growth. This approach utilizes an object

Area of Science:

  • Computer Science, Artificial Intelligence
  • Image Recognition
  • Machine Learning

Background:

  • Higher-order neural networks often exhibit combinatorial growth in size with increasing image dimensions.
  • Achieving invariant recognition (position, orientation) is a key challenge in computer vision.

Purpose of the Study:

  • Introduce a second-order neural network architecture for invariant object recognition.
  • Address the issue of combinatorial network size growth in image processing.
  • Investigate the role of an object's line-segment spectrum in network design.

Main Methods:

  • Developed a second-order neural network architecture.
  • Introduced the concept of an object's line-segment spectrum to determine network weights.
  • Implemented a multi-resolution training approach for network optimization.

Related Experiment Videos

Main Results:

  • The proposed network achieves invariant recognition concerning object position and orientation.
  • Network size does not grow combinatorially with image size.
  • Training time is dependent on object size, not image size.
  • Multi-resolution training reduced training time and improved performance on alphabet recognition.

Conclusions:

  • The second-order architecture offers an efficient solution for invariant object recognition.
  • The line-segment spectrum provides a novel approach to defining network weights.
  • Multi-resolution training enhances performance and efficiency in this specific application.