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

Expression-invariant representations of faces.

Alexander M Bronstein1, Michael M Bronstein, Ron Kimmel

  • 1Department of Computer Science, The Technion--Israel Institute of Technology, Haifa 32000. alexbron@ieee.org

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
|February 8, 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

The intermediate-risk gap in AI-based breast cancer stratification - Authors' reply.

The Lancet. Oncology·2026
Same author

Prediction of OncotypeDX recurrence score using hematoxylin and eosin-stained whole slide images.

NPJ breast cancer·2026
Same author

Description of a collaborative sperm whale birth and shifts in coda vocal styles during key events.

Scientific reports·2026
Same author

Deep learning on histopathological images to predict breast cancer recurrence risk and chemotherapy benefit: a multicentre, model development and validation study.

The Lancet. Oncology·2026
Same author

Deep Learning on Histopathological Images to Predict Breast Cancer Recurrence Risk and Chemotherapy Benefit.

medRxiv : the preprint server for health sciences·2025
Same author

Prediction of B/T Subtype and ETV6-RUNX1 Translocation in Pediatric Acute Lymphoblastic Leukemia by Deep Learning Analysis of Giemsa-Stained Whole Slide Images of Bone Marrow Aspirates.

Pediatric blood & cancer·2025
Same journal

Style-Aware Contrastive Test-Time Adaptation: A Dual-Cache Model for Robust Vision-Language Alignment.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

Semantic Frame Interpolation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

Physics-Guided Cross-Modal Decoupling with Test-Time Adaptation for Hyperspectral Image Restoration.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

Change-Prior-Guided Unsupervised Change Detection of Heterogeneous Remote Sensing Images.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

AgonicDreamer: Enhancing Multi-View Consistency in Text-to-3D Generation via Rectified Score Distillation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

BiCM-Prompt: Bidirectional Cross-Modal Prompt Tuning for Class-Incremental Learning on Multisource Remote Sensing Images.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
See all related articles

This study introduces a geometric model for expression-invariant face representation, using spherical embedding to minimize distortions. This approach improves facial recognition accuracy by better capturing intrinsic geometric structures.

Area of Science:

  • Computer Vision
  • Geometric Deep Learning
  • Biometrics

Background:

  • Facial expression variations pose challenges for accurate human face recognition.
  • Developing expression-invariant representations is crucial for robust facial analysis.

Purpose of the Study:

  • To propose and validate a novel geometric model for constructing expression-invariant face representations.
  • To investigate the impact of embedding space geometry on representation accuracy.

Main Methods:

  • Describing facial expressions as isometric deformations of the facial surface.
  • Embedding intrinsic facial geometry into a low-dimensional space.
  • Comparing spherical embedding with Euclidean embedding for metric distortion reduction.

Related Experiment Videos

Main Results:

  • A simple geometric model effectively describes facial expressions as surface deformations.
  • Spherical embedding yields smaller metric distortions compared to Euclidean embedding.
  • Reduced embedding error correlates with improved facial recognition performance.

Conclusions:

  • The proposed geometric model and spherical embedding offer a promising approach for expression-invariant face representation.
  • Optimizing embedding space geometry is key to enhancing the accuracy of facial recognition systems.