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

Permutation coding technique for image recognition systems.

Ernst M Kussul1, Tatiana N Baidyk, Donald C Wunsch

  • 1Lab of Micromechanics and Mechatronics, Center of Applied Science and Technological Development, National Autonomous University of Mexico, Mexico City 04510, Mexico. ekussul@servidor.unam.mx

IEEE Transactions on Neural Networks
|November 30, 2006
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

Current state of the art of new prostate MRI technologies and potential future developments.

BJR open·2026
Same author

Prostate Cancer: Current Status of Novel Molecular Imaging and Future Prospects.

European urology focus·2025
Same author

DeepART: Deep gradient-free local learning with adaptive resonance.

Neural networks : the official journal of the International Neural Network Society·2025
Same author

Adaptive Nussbaum Design for Nonholonomic Systems With Asymptotic Stabilization Against False Data Injection.

IEEE transactions on cybernetics·2025
Same author

The visualization of Orphadata neurology phenotypes.

Frontiers in digital health·2023
Same author

Subtypes of relapsing-remitting multiple sclerosis identified by network analysis.

Frontiers in digital health·2023
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 novel image recognition system using random local descriptors and permutation coding. The method achieves highly accurate results, with error rates as low as 0.44% on MNIST and 0.1% on ORL datasets.

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Machine Learning

Background:

  • Image recognition systems require robust feature extraction and classification methods.
  • Existing techniques may struggle with variations in feature position and small image displacements.
  • Developing invariant and generalizable image descriptors is crucial for accurate recognition.

Purpose of the Study:

  • To propose a novel image recognition system combining random local descriptors (RLDs) and permutation coding.
  • To enhance recognition accuracy by incorporating feature position information and achieving invariance to small displacements.
  • To evaluate the system's performance on diverse image recognition tasks.

Main Methods:

  • Feature extraction using Random Local Descriptors (RLDs).

Related Experiment Videos

  • Encoding detected features and their positions using permutation coding for displacement invariance.
  • Utilizing the generated code as input for a neural classifier.
  • Testing on handwritten digit (MNIST), face (ORL), and microobject shape recognition datasets.

    • Main Results:

    • Achieved a 0.44% error rate on the Modified National Institute of Standards and Technology (MNIST) database.
    • Achieved a 0.1% error rate on the Olivetti Research Laboratory (ORL) face database.
    • Demonstrated promising performance across multiple image recognition benchmarks.

    Conclusions:

    • The proposed system effectively combines RLDs and permutation coding for generalizable image description.
    • The method achieves high accuracy and invariance, outperforming existing approaches.
    • The system shows significant potential for various real-world image recognition applications.