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

Gabor wavelet associative memory for face recognition.

Haihong Zhang1, Bailing Zhang, Weimin Huang

  • 1Institute for Infocomm Research, Singapore 119613. hhzhang@i2r.a-star.edu.sg

IEEE Transactions on Neural Networks
|March 1, 2005
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

Self-directed learning ability and online student engagement among nursing students: the mediating role of information literacy and the moderating role of self-control.

Frontiers in psychology·2026
Same author

Ketohexokinase: A central mediator of fructose-associated pathogenesis and promising therapeutic target.

Pharmacological research·2026
Same author

C2 Laminar screw-screw assembly for the cranio-cervical junction.

Frontiers in surgery·2026
Same author

Editorial Expression of Concern: Integrating bioinformatics and experimental validation to Investigate IRF1 as a novel biomarker for nucleus pulposus cells necroptosis in intervertebral disc degeneration.

Scientific reports·2026
Same author

Physics-informed Koopman-constrained implicitQ-learning for safe offline reinforcement learning in mechanical ventilation.

Biomedical physics & engineering express·2026
Same author

Disrupted anastomotic pseudoaneurysm in arteriovenous grafts: an etiology-driven case series with a proposed preliminary management framework.

BMC nephrology·2026
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

A novel Gabor wavelet associative memory (GWAM) system integrates Gabor wavelet networks (GWN) and kernel associative memory (KAM) for superior face recognition. This high-performance system achieves excellent accuracy on benchmark datasets.

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Machine Learning

Background:

  • Face recognition systems are crucial for security and identification.
  • Existing methods like kernel associative memory (KAM) have limitations in representation capability.
  • Advancements in neural network models offer potential for improved face recognition.

Purpose of the Study:

  • To introduce a novel, high-performance face recognition system named Gabor wavelet associative memory (GWAM).
  • To leverage the representational strengths of Gabor wavelet networks (GWN) and kernel associative memory (KAM).
  • To evaluate the recognition accuracy and robustness of the proposed GWAM system.

Main Methods:

  • Combining Gabor wavelet network (GWN) and kernel associative memory (KAM) into a unified Gabor wavelet associative memory (GWAM) structure.

Related Experiment Videos

  • Conducting extensive experiments using three benchmark face databases: FERET, Olivetti-Oracle Research Lab (ORL), and AR face database.
  • Evaluating performance against varying illumination conditions.

    • Main Results:

    • The GWAM system demonstrated superior representation capability compared to KAM.
    • Achieved high recognition accuracies of 99.3% on the FERET database and 100% on the ORL database.
    • Exhibited very robust performance on the AR face database under challenging illumination variations.

    Conclusions:

    • The proposed Gabor wavelet associative memory (GWAM) system offers a significant advancement in face recognition technology.
    • GWAM's combined architecture provides superior performance and robustness compared to existing methods.
    • The system's high accuracy and resilience make it a promising solution for real-world face recognition applications.