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-based kernel PCA with fractional power polynomial models for face recognition.

Chengjun Liu1

  • 1Department of Computer Science, New Jersey Institute of Technology, Newark, NJ 07102, USA. liu@cs.njit.edu

IEEE Transactions on Pattern Analysis and Machine Intelligence
|October 6, 2004
PubMed
Summary

This study introduces a new Gabor-based kernel Principal Component Analysis (PCA) method for face recognition. It effectively handles variations in illumination and expression, improving recognition accuracy on challenging datasets.

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

Inhalation of Environmental Polystyrene Micro/Nanoplastics Induces Pulmonary Toxicity and Synergistically Exacerbates Acute Lung Injury in Male Mice.

Journal of applied toxicology : JAT·2026
Same author

The relationship between nutritional management and prognosis in children on prolonged mechanical ventilation.

Journal of pediatric gastroenterology and nutrition·2026
Same author

SLC39A1 sustains mitochondrial integrity in alveolar epithelium during acute lung injury.

Experimental cell research·2026
Same author

Beyond Net Ultrafiltration Rate: A Precision Fluid Management Paradigm Integrating Three Key Parameters for Pediatric Continuous Renal Replacement Therapy.

Critical care explorations·2026
Same author

Association between platelet-albumin-bilirubin score and 30-day in-hospital mortality in patients with sepsis: evidence from a large database and machine learning modeling.

BMC infectious diseases·2026
Same author

Clinical characteristics and inflammatory response of adenovirus viremia in children with severe adenoviral pneumonia: a prospective cohort study.

BMC infectious diseases·2026

Area of Science:

  • Computer Vision
  • Machine Learning
  • Biometrics

Background:

  • Face recognition systems struggle with variations in illumination and facial expressions.
  • Kernel Principal Component Analysis (PCA) is a powerful technique for non-linear dimensionality reduction.
  • Gabor wavelets offer robust feature extraction for images, capturing spatial and frequency information.

Purpose of the Study:

  • To develop a novel Gabor-based kernel PCA method for enhanced face recognition.
  • To integrate Gabor wavelet features with kernel PCA using fractional power polynomial models.
  • To evaluate the proposed method's performance on diverse face recognition tasks.

Main Methods:

  • Utilizing Gabor wavelets to extract discriminative facial features.

Related Experiment Videos

  • Extending kernel PCA with fractional power polynomial models.
  • Applying kernel PCA eigenvectors with positive eigenvalues for feature derivation.
  • Testing the method on FERET and CMU PIE face databases.

    • Main Results:

    • The Gabor-based kernel PCA method with fractional power polynomial models demonstrated effective face recognition.
    • The method showed strong performance on both frontal and pose-angled face recognition tasks.
    • Comparative analysis confirmed the superiority of the proposed method over traditional PCA and other kernel PCA variants.

    Conclusions:

    • The proposed Gabor-based kernel PCA method offers a robust solution for face recognition.
    • Fractional power polynomial kernels enhance kernel PCA performance in face recognition.
    • The integration of Gabor features and kernel PCA provides a powerful framework for biometric identification.