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

Weighted piecewise LDA for solving the small sample size problem in face verification.

Marios Kyperountas1, Anastasios Tefas, Ioannis Pitas

  • 1Department of Informatics, Aristotle University of Thessaloniki, Thessaloniki 54006, Greece. mkyper@aiia.csd.auth.gr

IEEE Transactions on Neural Networks
|March 28, 2007
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

Photonic Kolmogorov-Arnold networks based on self-phase modulation in nonlinear waveguides.

Optics letters·2026
Same author

LIX: Implicitly Infusing Spatial Geometric Prior Knowledge Into Visual Semantic Segmentation for Autonomous Driving.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2025
Same author

Comparison of ChatGPT-3.5 and GPT-4 as potential tools in artificial intelligence-assisted clinical practice in renal and liver transplantation.

World journal of transplantation·2025
Same author

Inducing Neural Collapse via Anticlasses and One-Cold Cross-Entropy Loss.

IEEE transactions on neural networks and learning systems·2025
Same author

Sign potential-driven multiplicative optimization for robust deep reinforcement learning.

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

These Maps Are Made by Propagation: Adapting Deep Stereo Networks to Road Scenarios With Decisive Disparity Diffusion.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2025

A new algorithm addresses the small sample size problem in face verification using Fisher's criterion. This method enhances accuracy by using weighted hyperplanes and outlier removal for better performance.

Area of Science:

  • Computer Science
  • Biometrics
  • Machine Learning

Background:

  • Face verification systems often struggle with the small sample size (SSS) problem due to insufficient training data.
  • This limitation leads to inaccurate estimations of decision boundaries, hindering performance.
  • Traditional Linear Discriminant Analysis (LDA) can be suboptimal in such scenarios.

Purpose of the Study:

  • To introduce and evaluate a novel algorithm designed to improve face verification performance.
  • To provide a general solution for the small sample size (SSS) problem in the context of face recognition.
  • To enhance the accuracy of discriminant hyperplanes and similarity score combinations.

Main Methods:

  • The algorithm employs a two-phase approach to overcome the SSS problem.

Related Experiment Videos

  • Phase one utilizes weighted piecewise discriminant hyperplanes for improved classification accuracy over standard LDA.
  • Phase two refines person-specific similarity scores and incorporates an outlier removal process.

    • Main Results:

    • The proposed algorithm was tested on the M2VTS and XM2VTS frontal face databases.
    • Experimental results demonstrate a significant improvement in face verification performance.
    • The method effectively addresses the challenges posed by limited training samples.

    Conclusions:

    • The novel algorithm offers a robust solution for the small sample size problem in face verification.
    • The combination of weighted hyperplanes and score refinement substantially boosts system accuracy.
    • This framework presents a promising advancement for reliable biometric identification systems.