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

MPCA: Multilinear Principal Component Analysis of Tensor Objects.

Haiping Lu1, Konstantinos N Kostas Plataniotis, Anastasios N Venetsanopoulos

  • 1Department of Electrical and Computer Engineering, University of Toronto, Toronto, ON M5S 3G4, Canada.

IEEE Transactions on Neural Networks
|February 14, 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

Discovery of a potential novel pharmacogenomic biomarker on ANK3 gene for liafensine, a triple reuptake inhibitor for treatment-resistant depression.

Translational psychiatry·2026
Same author

Geometry-Aware Line Graph Transformer Pretraining for Molecular Property Prediction.

IEEE transactions on neural networks and learning systems·2026
Same author

Three-Dimensional Evaluation of Zygomaticomaxillary Complex Displacement and Rotational Centre in Adults Induced by Maxillary Skeletal Expander, Analysed With CBCT and Heuristic Search Algorithm.

Orthodontics & craniofacial research·2026
Same author

Interpretable Multimodal Learning for Cardiovascular Hemodynamics Assessment.

IEEE transactions on medical imaging·2026
Same author

Expert consensus on orthodontic-associated alveolar ridge augmentation for adult patients.

International journal of oral science·2026
Same author

Classifying the Stoichiometry of Virus-like Particles with Interpretable Machine Learning.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025
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 multilinear principal component analysis (MPCA) for tensor feature extraction in computer vision. MPCA offers a superior method for analyzing complex data like images and videos, outperforming traditional PCA techniques.

Area of Science:

  • Computer Vision
  • Pattern Recognition
  • Machine Learning

Background:

  • Many real-world objects, including images and video sequences, are naturally represented as tensors or multilinear arrays.
  • Existing feature extraction methods like Principal Component Analysis (PCA) have limitations when applied to high-dimensional tensor data.

Purpose of the Study:

  • To introduce a novel Multilinear Principal Component Analysis (MPCA) framework for effective tensor object feature extraction.
  • To develop and analyze methods for determining appropriate subspace dimensionality within the MPCA framework.
  • To propose a tensor object recognition system incorporating discriminative feature selection and classification for applications like gait recognition.

Main Methods:

  • The proposed MPCA framework iteratively determines a multilinear projection to capture maximal variation in tensorial input data.

Related Experiment Videos

  • The framework decomposes the complex problem into a series of manageable multiple projection subproblems.
  • A discriminative tensor feature selection mechanism and a novel classification strategy are introduced for object recognition.

    • Main Results:

    • The MPCA framework demonstrates superior performance compared to classical PCA and its 2-D variant.
    • An MPCA-based gait recognition system achieved highly competitive performance, favorably comparing to state-of-the-art methods.
    • The utility of MPCA as a powerful feature extraction tool for tensor objects is validated.

    Conclusions:

    • MPCA provides an effective and advanced approach for feature extraction from tensor objects in computer vision and pattern recognition.
    • The proposed MPCA framework surpasses existing methods by handling the inherent multilinear structure of data more effectively.
    • MPCA shows significant promise for improving recognition tasks, as evidenced by its strong performance in gait recognition applications.