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

Comparing human and automatic face recognition performance.

Andy Adler1, Michael E Schuckers

  • 1Systems and Computer Engineering, Carleton University, Ottawa, ON K1S 5B6, Canada. adler@site.uOttawa.ca

IEEE Transactions on Systems, Man, and Cybernetics. Part B, Cybernetics : a Publication of the IEEE Systems, Man, and Cybernetics Society
|October 12, 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

Grading quality score of contrast electrical impedance tomography for lung ventilation-perfusion: development and preliminary evaluation of the impedance-time curve.

Respiratory medicine·2026
Same author

Thoracic electrical impedance tomography using a two-plane electrode configuration in horses.

Equine veterinary journal·2026
Same author

A robust temporal metric of ventilation inhomogeneity in electrical impedance tomography.

Physiological measurement·2026
Same author

Lung perfusion estimation by saline-contrast EIT without breath hold: a randomized cross-over trial.

Critical care (London, England)·2026
Same author

Comparison of early and late time-controlled adaptive ventilation on pulmonary gas exchange in anesthetized horses.

Veterinary anaesthesia and analgesia·2025
Same author

Bedside assessment of lung ventilation, recruitability and optimal PEEP by 3D-EIT and 2D-EIT in ARDS patients: a prospective study.

Intensive care medicine·2025
Same journal

Strategic Ability Updating in Concurrent Games by Coalitional Commitment.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2015
Same journal

Meta-Analysis of the First Facial Expression Recognition Challenge.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2012
Same journal

Adjustable model-based fusion method for multispectral and panchromatic images.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2012
Same journal

Face Feature Weighted Fusion Based on Fuzzy Membership Degree for Video Face Recognition.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2012
Same journal

A New Adaptive Fast Cellular Automaton Neighborhood Detection and Rule Identification Algorithm.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2012
Same journal

Human-arm-and-hand-dynamic model with variability analyses for a stylus-based haptic interface.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2012
See all related articles

This study compares automatic face recognition (AFR) systems with human face recognition (HFR). While AFR technology has improved significantly, human performance still surpasses some advanced systems, highlighting areas for future development in biometric security.

Area of Science:

  • Biometrics
  • Computer Vision
  • Human-Computer Interaction

Background:

  • Face recognition technologies have advanced significantly, leading to widespread use in security and commerce.
  • Human face recognition (HFR) is known for its high accuracy, prompting comparisons with automatic face recognition (AFR) systems.
  • Evaluating and comparing the performance of different biometric systems, including AFR and HFR, requires robust statistical methods.

Purpose of the Study:

  • To compare the biometric performance of commercial automatic face recognition (AFR) systems against human face recognition (HFR).
  • To develop novel statistical methods for evaluating and comparing the performance of biometric systems.
  • To analyze the historical performance trends of AFR algorithms from 1999 to 2006 relative to human performance.

Main Methods:

Related Experiment Videos

  • Verification tests were conducted using human subjects (HFR) and commercial AFR systems with face-image pairs.
  • Subjects classified image pairs using a defined scale, while AFR systems generated biometric match scores.
  • Two new statistical techniques were developed: score distribution normalization using polar coordinates and average detection error tradeoff (DET) curve calculation.

Main Results:

  • Automatic face recognition algorithms have shown dramatic performance improvements between 1999 and 2006.
  • In 2006, the best AFR systems were compared to human performance.
  • 29.2% of human subjects performed better than the best 2006 AFR system, while 37.5% performed worse.

Conclusions:

  • While AFR technology has advanced considerably, human face recognition remains a benchmark for performance.
  • The developed statistical methods provide a framework for objective comparison of biometric systems.
  • Further research is needed to bridge the remaining performance gap between advanced AFR systems and human capabilities.