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 Video

Updated: Jun 1, 2026

Building Up Skin Models for Numerous Applications - from Two-Dimensional (2D) Monoculture to Three-Dimensional (3D) Multiculture
08:32

Building Up Skin Models for Numerous Applications - from Two-Dimensional (2D) Monoculture to Three-Dimensional (3D) Multiculture

Published on: October 20, 2023

Unconstrained Pose-Invariant Face Recognition Using 3D Generic Elastic Models.

Utsav Prabhu, Jingu Heo, Marios Savvides

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |June 15, 2011
    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

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

    NeuroImage·2025
    Same author

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

    NeuroImage·2023
    Same author

    Face recognition from research brain PET: An unexpected PET problem.

    NeuroImage·2022
    Same author

    Content-Aware Eye Tracking for Autostereoscopic 3D Display.

    Sensors (Basel, Switzerland)·2020
    Same author

    Autostereoscopic 3D display using directional subpixel rendering.

    Optics express·2018
    Same author

    Reformulating Level Sets as Deep Recurrent Neural Network Approach to Semantic Segmentation.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2018
    Same journal

    TraGraph-GS: Trajectory Graph-based Gaussian Splatting for Arbitrary Large-Scale Scene Rendering.

    IEEE transactions on pattern analysis and machine intelligence·2026
    Same journal

    SWIFT: A Small-World Interaction Framework for Flow-Aware Trajectory Prediction in Autonomous Driving.

    IEEE transactions on pattern analysis and machine intelligence·2026
    Same journal

    HardFlow: Hard-Constrained Sampling for Flow-Matching Models Via Trajectory Optimization.

    IEEE transactions on pattern analysis and machine intelligence·2026
    Same journal

    Industrial Brain: Self-Evolving Neuro-Symbolic Autonomy with Causal Resilience for Cyber-Physical Systems.

    IEEE transactions on pattern analysis and machine intelligence·2026
    Same journal

    Adaptive Hardness-Driven Dictionary Distillation for Incomplete Streaming View Clustering.

    IEEE transactions on pattern analysis and machine intelligence·2026
    Same journal

    Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation.

    IEEE transactions on pattern analysis and machine intelligence·2026
    See all related articles

    This study introduces a novel method for unconstrained pose-invariant face recognition, creating 3D face models from single images. The approach achieves high accuracy in real-world scenarios, overcoming limitations of traditional methods.

    Area of Science:

    • Computer Vision
    • Biometrics
    • Artificial Intelligence

    Background:

    • Traditional face recognition struggles with real-world variations like pose and illumination.
    • Uncontrolled environments pose significant challenges for robust face identification systems.

    Purpose of the Study:

    • To develop a pose-invariant face recognition method for unconstrained, real-world scenarios.
    • To enable accurate face recognition despite variations in subject pose and imaging conditions.

    Main Methods:

    • Constructing 3D face models from single 2D images using the 3D Generic Elastic Model (3D GEM).
    • Synthesizing novel 2D pose views from 3D models for matching.
    • Estimating query pose via facial landmark annotation and linear regression.
    • Rendering 3D models at various poses for comparison with the test query using normalized correlation matching.

    More Related Videos

    Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans
    10:23

    Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans

    Published on: September 8, 2023

    Related Experiment Videos

    Last Updated: Jun 1, 2026

    Building Up Skin Models for Numerous Applications - from Two-Dimensional (2D) Monoculture to Three-Dimensional (3D) Multiculture
    08:32

    Building Up Skin Models for Numerous Applications - from Two-Dimensional (2D) Monoculture to Three-Dimensional (3D) Multiculture

    Published on: October 20, 2023

    Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans
    10:23

    Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans

    Published on: September 8, 2023

    Main Results:

    • Demonstrated high recognition accuracy on challenging datasets and video sequences.
    • Achieved robust performance in both controlled and uncontrolled real-world settings.
    • The implemented method is fast and effective for pose-invariant face recognition.

    Conclusions:

    • The proposed 3D model-based pose synthesis method significantly improves face recognition in unconstrained environments.
    • This technique offers a viable solution for real-world face identification challenges.
    • The approach effectively handles pose variations, enhancing recognition accuracy and robustness.