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

Deformation modeling for robust 3D face matching.

Xiaoguang Lu1, Anil Jain

  • 1Siemens Corporate Research, East Princeton, NJ 08540, USA. lvxiaogu@ieee.org

IEEE Transactions on Pattern Analysis and Machine Intelligence
|June 21, 2008
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

An Integrated Rotation-Programmed and Gravity-Driven Microfluidic Platform for Direct Bacterial Detection from Whole Blood.

Analytical chemistry·2026
Same author

Phosphate binders and the gut microbiota in chronic kidney disease: mechanisms, mixed evidence, and clinical considerations.

Journal of nephrology·2026
Same author

3D-Photothermal Ultrafast PCR via rGO/PDMS-Based Microfluidic Chip and Its Application in Rapid Identification of Gram-Negative Bacteria in Whole Blood.

ACS applied materials & interfaces·2026
Same author

Single Nuclei Isolation from Coronary Endarterectomy Tissue of Coronary Artery Bypass Graft Patients.

Journal of visualized experiments : JoVE·2026
Same author

50 Years of Automated Face Recognition.

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

Outcome of del Nido versus St. Thomas cardioplegia solution in adult mitral valve replacement surgery for rheumatic mitral valve disease.

Perfusion·2026
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 3D face recognition method to handle facial expressions and pose variations. The new approach enhances 3D face matching accuracy by modeling non-rigid facial deformations.

Area of Science:

  • Computer Science
  • Biometrics
  • Computer Vision

Background:

  • Current 2D face recognition systems struggle with pose and lighting variations.
  • 3D face recognition offers pose invariance but is sensitive to non-rigid facial movements like expressions.
  • Storing multiple templates for various expressions is impractical for large databases.

Purpose of the Study:

  • To develop a robust 3D face recognition system capable of handling non-rigid facial deformations and multi-view pose changes.
  • To create a user-specific deformable 3D face model for accurate matching.
  • To improve the accuracy of 3D face matching over existing methods.

Main Methods:

  • A hierarchical geodesic-based resampling approach was used to extract landmarks for modeling facial deformations.

Related Experiment Videos

  • Facial deformations from a control group were synthesized onto a 3D neutral model to create deformed templates.
  • A generative deformable model was built and fitted to test scans for matching distance computation.

    • Main Results:

    • A fully automatic and prototypic 3D face matching system was developed.
    • The proposed deformation modeling scheme significantly increased 3D face matching accuracy.
    • The system effectively handles both non-rigid deformations and pose variations.

    Conclusions:

    • The developed facial surface modeling and matching scheme provides a practical solution for 3D face recognition.
    • The user-specific deformable model approach enhances accuracy by accounting for facial movement.
    • This method offers a promising advancement for 3D face recognition systems in real-world applications.