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

Face recognition with perspective transformation.

Chang Hong Liu1, Avi Chaudhuri

  • 1Department of Psychology, McGill University, Montréal, Que. H3A 1B1, Canada. c.h.liu@hull.ac.uk

Vision Research
|September 16, 2003
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 impact of forensic delay: facilitating facial composite construction using an early-recall retrieval technique.

Ergonomics·2025
Same author

Distinguishing the roles of edge, color, and other surface information in basic and superordinate scene representation.

NeuroImage·2025
Same author

Common intentional binding effects across diverse sensory modalities in touch-free voluntary actions.

Consciousness and cognition·2024
Same author

Relationship between types of anxiety and the ability to recognize facial expressions.

Acta psychologica·2023
Same author

Decoding the temporal representation of facial expression in face-selective regions.

NeuroImage·2023
Same author

Voice attractiveness and decision making in third-party punishment.

PsyCh journal·2023
Same journal

Computational and mathematical models in vision: Quantitative approaches to understanding visual perception.

Vision research·2026
Same journal

Complex interactions between lightness, chroma, and hue in color ensemble perception.

Vision research·2026
Same journal

Driving with autism spectrum disorder: Exploring the impact of tactile hazard warnings on gaze behavior and hazard responses.

Vision research·2026
Same journal

Early visual processing in adults with ADHD: evidence from contrast sensitivity, spatial integration, and external noise.

Vision research·2026
Same journal

Pupil reflexes generate the peripheral drift illusion due to ON/OFF motion responses.

Vision research·2026
Same journal

Perceived direction of glass patterns can flip by 90°: A neural model.

Vision research·2026
See all related articles

Face recognition is impaired by perspective changes. Performance depends on the degree of transformation, with larger changes causing more difficulty. Local features are more important than global perspective for recognition.

Area of Science:

  • Cognitive Psychology
  • Computer Vision
  • Neuroscience

Background:

  • Human face recognition is robust to variations in viewpoint.
  • Understanding how perspective transformation affects face recognition is crucial for artificial intelligence and human perception studies.

Purpose of the Study:

  • To investigate the impact of perspective transformation magnitude on face recognition.
  • To determine whether local features or global perspective coherence drives face transfer.

Main Methods:

  • A yes/no recognition task using face stimuli with varying degrees of perspective convergence (0, 10, 42 degrees).
  • Experiment 1: Tested recognition after learning faces at different perspectives and testing at orthogonal view.
  • Experiment 2: Created composite faces with identical local features but impossible global perspective transformations to assess transfer.

Related Experiment Videos

Main Results:

  • Recognition performance significantly decreased with increasing magnitude of perspective transformation.
  • Large perspective changes (42° to 0°) caused the most significant recognition impairment.
  • Transfer was high when local features were similar, even with impossible global perspective transformations, indicating insensitivity to global coherence.

Conclusions:

  • Face recognition is highly sensitive to the magnitude of perspective transformation during training and testing.
  • Local featural information plays a dominant role in face recognition transfer, overriding global perspective inconsistencies.