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

Evolving faces from principal components.

P J Hancock1

  • 1Department of Psychology, University of Stirling, Scotland. pjbh1@stir.ac.uk

Behavior Research Methods, Instruments, & Computers : a Journal of the Psychonomic Society, Inc
|June 30, 2000
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

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

A radio transient with unusually slow periodic emission.

Nature·2022
Same author

Groundwater Ecosystems Vary with Land Use across a Mixed Agricultural Landscape.

Journal of environmental quality·2013
Same author

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

Vision research·2001
Same author

The crystal structure of human protein farnesyltransferase reveals the basis for inhibition by CaaX tetrapeptides and their mimetics.

Proceedings of the National Academy of Sciences of the United States of America·2001
Same author

Effects of dizocilpine (MK 801) on noradrenaline, serotonin and dopamine release and uptake.

Neuroreport·2000
Same journal

Real-time language comprehension research using the Apple-Psych system.

Behavior research methods, instruments, & computers : a journal of the Psychonomic Society, Inc·2014
Same journal

Constraints on the perception of synthetic speech generated by rule.

Behavior research methods, instruments, & computers : a journal of the Psychonomic Society, Inc·2014
Same journal

Perception of synthetic speech produced automatically by rule: Intelligibility of eight text-to-speech systems.

Behavior research methods, instruments, & computers : a journal of the Psychonomic Society, Inc·2012
Same journal

Ninety-three pictures and 108 questions for the elicitation of homophones.

Behavior research methods, instruments, & computers : a journal of the Psychonomic Society, Inc·2011
Same journal

Free-association norms for the Spanish names of the Snodgrass and Vanderwart pictures.

Behavior research methods, instruments, & computers : a journal of the Psychonomic Society, Inc·2005
Same journal

French normative data and naming times for action pictures.

Behavior research methods, instruments, & computers : a journal of the Psychonomic Society, Inc·2005
See all related articles

This study introduces a novel system using genetic algorithms to evolve faces based on user preferences. It demonstrates the creation of plausible, randomly generated photographic face images through statistical analysis and principal component analysis.

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Biometric Systems

Background:

  • Generating realistic human faces computationally is a complex challenge.
  • Previous methods often lack user interactivity or statistical rigor.
  • The need for systems that can synthesize novel facial imagery persists.

Purpose of the Study:

  • To develop a system capable of evolving faces using genetic algorithms.
  • To leverage statistical analysis of existing faces for novel generation.
  • To enable user-driven evolution of synthetic facial images.

Main Methods:

  • Statistical analysis of a face dataset to derive descriptive features.
  • Morphing techniques to standardize face shapes for analysis.
  • Principal Component Analysis (PCA) applied to shape-free images (eigenfaces) and shape vectors (eigenshapes).

Related Experiment Videos

  • Recombination of image and shape components to generate new faces.

    • Main Results:

    • The system successfully generated novel faces through recombination of eigenfaces and eigenshapes.
    • The generated faces were plausible and appeared as randomly produced photographic images.
    • The prototype demonstrated the efficacy of the statistical and evolutionary approach.

    Conclusions:

    • A genetic algorithm-based system can effectively evolve faces.
    • Statistical analysis and PCA are powerful tools for facial image synthesis.
    • The system offers a method for creating realistic, user-guided synthetic faces.