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 appearance-based 3-D object recognition using independent component analysis.

H S Sahambi1, K Khorasani

  • 1Dept. of Electr. and Comput. Eng., Concordia Univ., Montreal, Canada.

IEEE Transactions on Neural Networks
|February 2, 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

Distributed reconfigurable control strategies for switching topology networked multi-agent systems.

ISA transactions·2017
Same author

An ensemble of dynamic neural network identifiers for fault detection and isolation of gas turbine engines.

Neural networks : the official journal of the International Neural Network Society·2016
Same author

Hybrid fault diagnosis of nonlinear systems using neural parameter estimators.

Neural networks : the official journal of the International Neural Network Society·2013
Same author

Gene interaction networks based on kernel correlation metrics.

International journal of computational biology and drug design·2013
Same author

A recurrent neural-network-based sensor and actuator fault detection and isolation for nonlinear systems with application to the satellite's attitude control subsystem.

IEEE transactions on neural networks·2008
Same author

Application of adaptive constructive neural networks to image compression.

IEEE transactions on neural networks·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

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

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
Same journal

Data-based identification and control of nonlinear systems via piecewise affine approximation.

IEEE transactions on neural networks·2011
Same journal

Data-core-based fuzzy min-max neural network for pattern classification.

IEEE transactions on neural networks·2011
See all related articles

Independent Component Analysis (ICA) was explored for 3-D object recognition, outperforming Principal Component Analysis (PCA) on one dataset. However, ICA

Area of Science:

  • Computer Vision
  • Machine Learning
  • Pattern Recognition

Background:

  • Appearance-based 3-D object recognition (3DOR) is crucial for many applications.
  • Independent Component Analysis (ICA) shows promise in face recognition due to its use of high-order statistics.
  • Principal Component Analysis (PCA) relies on second-order statistics and may not capture all data redundancies.

Purpose of the Study:

  • To investigate the effectiveness of ICA in 3DOR compared to PCA.
  • To explore the utilization of redundant information in visual data for enhanced object recognition.
  • To determine if ICA's high-order statistics offer an advantage over PCA's lower-order statistics in 3DOR.

Main Methods:

  • Development of a neural network architecture based on ICA for 3DOR.

Related Experiment Videos

  • Comparison of ICA performance against PCA using two distinct image databases.
  • Analysis of image data captured by a CCD camera.

    • Main Results:

    • ICA outperformed PCA in object recognition accuracy on one of the two tested image databases.
    • ICA's performance was comparable to PCA on the second database, indicating no significant advantage.
    • The study highlights the data-dependent nature of ICA's effectiveness in 3DOR.

    Conclusions:

    • The application of ICA for 3D object recognition is not universally superior to PCA.
    • Recognition performance using ICA is highly dependent on the characteristics of the dataset.
    • Further research is needed to understand the factors influencing ICA's success in different recognition tasks.