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

Human and automatic face recognition: a comparison across image formats.

A M Burton1, P Miller, V Bruce

  • 1University of Glasgow, Department of Psychology, G12 8QQ, Glasgow, UK. mike@psy.gla.ac.uk

Vision Research
|November 17, 2001
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

Antibodies and Inflammation: Fecal Biomarkers of Gut Health in Domestic Ruminants.

Journal of experimental zoology. Part A, Ecological and integrative physiology·2025
Same author

Temperature-controlled Laminar Airflow (TLA) in symptomatic severe asthma - a post hoc analysis of severe exacerbations, quality of life and health economics.

BMC pulmonary medicine·2022
Same author

Evaluation of plasma nucleosome concentrations in dogs with a variety of common cancers and in healthy dogs.

BMC veterinary research·2022
Same author

GaLactic and Extragalactic All-sky Murchison Widefield Array survey eXtended (GLEAM-X) I: Survey Description and Initial Data Release.

Publications of the Astronomical Society of Australia : PASA·2022
Same author

The Impact of Climate Change on Healthcare.

Irish medical journal·2022
Same author

A radio transient with unusually slow periodic emission.

Nature·2022
Same journal

Editorial for VSI Amblyopia: Advances in Amblyopia Research.

Vision research·2026
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
See all related articles

Unfamiliar face matching is challenging for humans and machines. An automatic principal components analysis (PCA) system, optimized with the Mahalanobis metric, outperformed human performance in recognizing faces from different cameras.

Area of Science:

  • Computer Science
  • Cognitive Science
  • Biometrics

Background:

  • Human face recognition accuracy decreases with unfamiliar faces and varying image capture devices.
  • Automatic face recognition systems also struggle with image variability.

Purpose of the Study:

  • To compare the performance of a principal components analysis (PCA)-based automatic face recognition system against human subjects.
  • To evaluate different PCA system configurations, including various matching metrics and component numbers.

Main Methods:

  • An automatic face recognition system using principal components analysis (PCA) was developed.
  • The system's performance was evaluated using different distance metrics (Mahalanobis vs. Euclidean) and varying numbers of principal components.
  • Human subjects were tested on the same set of images for direct performance comparison.

Related Experiment Videos

Main Results:

  • PCA system performance was highly dependent on the chosen distance metric.
  • The Mahalanobis metric significantly outperformed the Euclidean metric for PCA-based face recognition.
  • Under optimal configurations, the PCA system demonstrated superior performance compared to human subjects in matching unfamiliar faces captured by different devices.

Conclusions:

  • Automatic face recognition systems, particularly PCA-based ones, can surpass human capabilities for unfamiliar face matching under specific conditions.
  • The findings suggest that human unfamiliar face recognition might rely on relatively simple input processing mechanisms.