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

Image-based face recognition under illumination and pose variations.

Shaohua Kevin Zhou1, Rama Chellappa

  • 1Center for Automation Research and Department of Electrical and Computer Engineering, University of Maryland, College Park, Maryland 20742, USA. kzhou@scr.siemens.com

Journal of the Optical Society of America. A, Optics, Image Science, and Vision
|February 19, 2005
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

Deep Learning for the Detection of Corneal Perforation on Anterior-Segment Optical Coherence Tomography in Microbial Keratitis.

Bioengineering (Basel, Switzerland)·2026
Same author

DuoMod-Net: Logarithmic balancing and geometric refinement for imbalanced semi-supervised medical image segmentation.

Patterns (New York, N.Y.)·2026
Same author

Deep Learning for Detection of Corneal Perforation on Anterior Segment Optical Coherence Tomography in Microbial Keratitis.

medRxiv : the preprint server for health sciences·2026
Same author

Recovering Pulse Waves From Video Using Deep Unrolling and Deep Equilibrium Models.

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

A self-supervised framework for emphysema anomaly detection and staging in computed tomography scans.

Patterns (New York, N.Y.)·2026
Same author

IRESeek: structure-informed deep learning method for accurate identification of internal ribosome entry sites in circular RNAs.

NAR genomics and bioinformatics·2026
Same journal

Multi-module collaborative optimization-driven fast speckle correlation imaging in variable environments.

Journal of the Optical Society of America. A, Optics, image science, and vision·2026
Same journal

Secrecy performance analysis of NOMA-UWOC systems over a vertically stratified WGG oceanic turbulence channel.

Journal of the Optical Society of America. A, Optics, image science, and vision·2026
Same journal

Backscattering of plane waves in a composite system containing a rough surface and anisotropic scatterers.

Journal of the Optical Society of America. A, Optics, image science, and vision·2026
Same journal

Aspherical surface construction methods based on extended Jacobi polynomials.

Journal of the Optical Society of America. A, Optics, image science, and vision·2026
Same journal

OCT sidelobe suppression method based on dual-path phase sinusoidal modulation and minimum value fusion.

Journal of the Optical Society of America. A, Optics, image science, and vision·2026
Same journal

Optical design concepts using wavelength-selective diffractive optics to enable miniaturized multimodal endoscopic imaging across separated spectral ranges.

Journal of the Optical Society of America. A, Optics, image science, and vision·2026
See all related articles

This study introduces an image-based face recognition method that works despite varying light and poses without 3D models. The approach creates an identity signature invariant to illumination and pose changes.

Area of Science:

  • Computer Vision
  • Biometrics
  • Machine Learning

Background:

  • Face recognition is challenging due to variations in illumination and pose.
  • Existing methods often require 3D models or struggle with simultaneous changes in identity, illumination, and pose.

Purpose of the Study:

  • To develop an image-based face recognition method that generalizes across illumination and pose variations.
  • To create an identity signature invariant to illumination and pose.

Main Methods:

  • An image-based approach is proposed, eliminating the need for explicit 3D models.
  • Subspace encoding is used to tackle identity variations.
  • A Lambertian reflectance model characterizes illumination.
  • A set of poses is treated collectively.

Related Experiment Videos

Main Results:

  • The method demonstrates generalization in identity and illumination dimensions.
  • It effectively handles a given set of poses.
  • Experiments on the Pose, Illumination, and Expression (PIE) database validate the approach's effectiveness.

Conclusions:

  • The proposed method offers robust face recognition under challenging illumination and pose conditions.
  • It provides an effective illumination- and pose-invariant identity signature.
  • This technique advances image-based face recognition without relying on 3D data.