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

Fusing face-verification algorithms and humans.

Alice J O'Toole1, Hervé Abdi, Fang Jiang

  • 1School of Behavioral and Brain Sciences (GR4.1), The University of Texas at Dallas, Richardson, TX 75083-0688, USA. otoole@utdallas.edu

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

Optimizing the mucosal frontier: longevity and epithelial barriers in prime-boost mRNA vaccine strategies.

Journal of translational medicine·2026
Same author

Development of a Machine Learning‑Based Prognostic Model for Intermediate Trophoblastic Tumors: A Single-Center Study With Web-Based Tool Implementation.

JCO precision oncology·2026
Same author

Temporal dynamics of adaptation to same- and other-race faces: buildup, decay and sustained effects.

Psychological research·2026
Same author

HIF-1α impairs NK cell differentiation-maturation and cytotoxicity in myelodysplastic syndrome via JAK1/STAT5/SOCS2 pathway.

Journal of immunology (Baltimore, Md. : 1950)·2026
Same author

Effects of dietary palygorskite supplementation on production performance and reproductive function of laying hens.

Poultry science·2026
Same author

covSTATIS: a multi-table technique for network neuroscience.

Aperture neuro·2026
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

Combining human and artificial intelligence significantly improves face recognition. Fusing algorithms and human experts using partial least square regression (PLSR) achieved near-perfect accuracy, outperforming individual systems.

Area of Science:

  • Computer Science
  • Biometrics
  • Artificial Intelligence

Background:

  • State-of-the-art face recognition algorithms exceed human accuracy under varying illumination.
  • Current accuracy rankings do not clarify if human and algorithmic performance are comparable or if fusion is beneficial.

Purpose of the Study:

  • To fuse human and algorithmic face recognition capabilities.
  • To determine if combining human and algorithmic approaches enhances face verification accuracy.

Main Methods:

  • Partial Least Square Regression (PLSR) was used to fuse similarity scores from seven Face Recognition Grand Challenge algorithms.
  • A jackknife procedure validated the generalizability of optimal score weightings.
  • Human subject similarity scores were integrated into the PLSR model.

Related Experiment Videos

Main Results:

  • Fusing algorithm similarity scores with optimal PLSR weights reduced the error rate twofold compared to the best algorithm.
  • Integrating human similarity scores into the PLSR model achieved near-perfect classification accuracy.

Conclusions:

  • Hybrid systems combining multiple algorithms and human expertise can maximize face verification accuracy.
  • Fusion of human and algorithmic face recognition offers superior performance over individual systems.