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 Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Adversarial rain attack and defensive deraining for DNN perception.

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

Measuring the potential risk of re-identification of imaging research participants from open-source automated face recognition software.

NeuroImage·2025
Same author

SODA: Spectral Orthogonal Decomposition Adaptation for Diffusion Models.

IEEE Winter Conference on Applications of Computer Vision. IEEE Winter Conference on Applications of Computer Vision·2025
Same author

Ethical-Lens: Curbing malicious usages of open-source text-to-image models.

Patterns (New York, N.Y.)·2025
Same author

Adversarial Exposure Attack on Diabetic Retinopathy Imagery Grading.

IEEE journal of biomedical and health informatics·2024
Same author

A face-off of MRI research sequences by their need for de-facing.

NeuroImage·2023

Related Experiment Video

Updated: Apr 27, 2026

Scanning Light Scattering Profiler SLPS Based Methodology to Quantitatively Evaluate Forward and Backward Light Scattering from Intraocular Lenses
06:55

Scanning Light Scattering Profiler SLPS Based Methodology to Quantitatively Evaluate Forward and Backward Light Scattering from Intraocular Lenses

Published on: June 6, 2017

6.9K

Subspace-based discrete transform encoded local binary patterns representations for robust periocular matching on

Felix Juefei-Xu, Marios Savvides

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |June 22, 2014
    PubMed
    Summary

    This study introduces a novel discrete transform encoded local binary patterns (DT-LBP) method for periocular recognition. DT-LBP significantly improves face recognition accuracy compared to traditional methods, offering robustness to variations.

    More Related Videos

    Dissection of Human Retina and RPE-Choroid for Proteomic Analysis
    06:54

    Dissection of Human Retina and RPE-Choroid for Proteomic Analysis

    Published on: November 12, 2017

    10.8K
    Author Spotlight: Accelerating Cognitive Impairment Research in Mice Through Stereotaxic Injection and Cost-Effective Dyes
    06:48

    Author Spotlight: Accelerating Cognitive Impairment Research in Mice Through Stereotaxic Injection and Cost-Effective Dyes

    Published on: July 19, 2024

    2.9K

    Related Experiment Videos

    Last Updated: Apr 27, 2026

    Scanning Light Scattering Profiler SLPS Based Methodology to Quantitatively Evaluate Forward and Backward Light Scattering from Intraocular Lenses
    06:55

    Scanning Light Scattering Profiler SLPS Based Methodology to Quantitatively Evaluate Forward and Backward Light Scattering from Intraocular Lenses

    Published on: June 6, 2017

    6.9K
    Dissection of Human Retina and RPE-Choroid for Proteomic Analysis
    06:54

    Dissection of Human Retina and RPE-Choroid for Proteomic Analysis

    Published on: November 12, 2017

    10.8K
    Author Spotlight: Accelerating Cognitive Impairment Research in Mice Through Stereotaxic Injection and Cost-Effective Dyes
    06:48

    Author Spotlight: Accelerating Cognitive Impairment Research in Mice Through Stereotaxic Injection and Cost-Effective Dyes

    Published on: July 19, 2024

    2.9K

    Area of Science:

    • Computer Vision
    • Biometrics
    • Pattern Recognition

    Background:

    • Periocular region recognition is crucial for biometrics, especially when full face data is unavailable or compromised.
    • Traditional methods using raw pixel intensity or basic Local Binary Patterns (LBP) have limitations in handling variations.
    • Large-scale datasets like NIST's FRGC ver2 are essential for evaluating biometric system performance.

    Purpose of the Study:

    • To develop and evaluate a robust periocular recognition system using a novel descriptor.
    • To compare the performance of periocular recognition against full-face recognition.
    • To introduce general frameworks for subspace modeling and descriptor creation in biometrics.

    Main Methods:

    • Employing subspace representations (PCA, UDA, KCDFA, KDA) on Discrete Transform encoded Local Binary Patterns (DT-LBP).
    • Utilizing the NIST Face Recognition Grand Challenge (FRGC) ver2 database, following Experiment 4 protocol for 1-to-1 matching.
    • Comparing periocular region performance with full-face recognition under various illumination preprocessing schemes.

    Main Results:

    • Subspace representation on DT-LBP significantly outperforms standard LBP and traditional subspace methods on raw pixel intensity.
    • Periocular recognition achieves performance close to full-face recognition, with only a minor reduction in verification rate.
    • The proposed DT-LBP descriptor outperformed eight other state-of-the-art descriptors in facial recognition tasks.

    Conclusions:

    • The proposed DT-LBP approach offers a significant advancement in periocular recognition accuracy and robustness.
    • Periocular recognition provides a viable alternative to full-face recognition, offering tolerance to expression, occlusion, and partial face matching.
    • The study presents two general frameworks for advanced biometric descriptor creation and subspace modeling.