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

Learning from humans: computational modeling of face recognition.

Christian Wallraven1, Adrian Schwaninger, Heinrich H Bülthoff

  • 1Max Planck Institute for Biological Cybernetics, Tübingen, Germany. christian.wallraven@tuebingen.mpg.de

Network (Bristol, England)
|April 14, 2006
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 importance of external features for categorizing ethnicity: can Koreans identify Korean, Japanese, and Chinese faces?

Perception·2026
Same author

More Than a Material: Social Interpretation Shapes the Hedonic Evaluation of Human Hand Touch.

IEEE transactions on haptics·2026
Same author

Unmasking deceptive decisions in a two-player competitive game: Integrating ERPs, spectral-perturbation signatures, and interpretable neural-network decoding.

Biological psychology·2026
Same author

Charting Decodability of Dynamic Facial Expressions in Young and Old Adults: Similarities and Differences.

Experimental neurobiology·2025
Same author

Seeing What Matters: Attentional (MIS-) Alignment between Humans and AI in VR-Simulated Prediction of Driving Accidents.

IEEE transactions on visualization and computer graphics·2025
Same author

Can impersonal touch replace interpersonal touch? An investigation using the rubber hand illusion.

PloS one·2025

This study introduces a novel computational face recognition system inspired by human cognitive processes. The model effectively mimics human face perception, achieving high accuracy even with significant viewpoint changes.

Area of Science:

  • Cognitive Science
  • Computer Vision
  • Biometrics

Background:

  • Human face recognition involves processing both configural (holistic) and component (feature-based) information.
  • Psychophysical studies provide insights into human visual perception mechanisms for faces.

Purpose of the Study:

  • To develop a computational face recognition architecture informed by cognitive research.
  • To model human performance in face recognition tasks using computational methods.
  • To enhance recognition system performance through interdisciplinary approaches.

Main Methods:

  • An appearance-based computational model was implemented using low-level visual features and their spatial relationships.
  • The model was designed to simulate the combined use of configural and component information observed in human face processing.

Related Experiment Videos

  • Computational experiments were conducted to evaluate recognition accuracy, particularly under varying viewing conditions.

    • Main Results:

    • The computational architecture successfully modeled key aspects of human performance observed in psychophysical studies.
    • The system demonstrated excellent face recognition capabilities, even when faces were presented with large view rotations.
    • The study validated the effectiveness of integrating cognitive principles into computational recognition systems.

    Conclusions:

    • Cognitive research findings can significantly improve the performance of computational face recognition systems.
    • The developed framework offers a robust approach to face recognition, adaptable to different viewing angles.
    • The research establishes a feedback loop between computational modeling and psychophysical experimentation for advancing face recognition technology.