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 different classifiers for automatic age estimation.

Andreas Lanitis1, Chrisina Draganova, Chris Christodoulou

  • 1Department of Computer Science and Engineering, Cyprus College, Nicosia, Cyprus. alanitis@cycollege.ac.cy

IEEE Transactions on Systems, Man, and Cybernetics. Part B, Cybernetics : a Publication of the IEEE Systems, Man, and Cybernetics Society
|September 17, 2004
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

In Reply: Comment on: The evolution and formalization of anesthesia assistant roles across Canada.

Canadian journal of anaesthesia = Journal canadien d'anesthesie·2025
Same author

In reply: Comment on: The evolution and formalization of anesthesia assistant roles across Canada.

Canadian journal of anaesthesia = Journal canadien d'anesthesie·2025
Same author

Post-processing enhances protein secondary structure prediction with second order deep learning and embeddings.

Computational and structural biotechnology journal·2025
Same author

The evolution and formalization of anesthesia assistant roles across Canada.

Canadian journal of anaesthesia = Journal canadien d'anesthesie·2024
Same author

Editorial: Selected papers from the 14th international neural coding workshop, Seattle, Washington.

Bio Systems·2022
Same author

An examination of difficulties accessing surgical care in Canada from 2005-2014: Results from the Canadian Community Health Survey.

PloS one·2020
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 quantitatively evaluates automatic age estimation using facial appearance models and various classifiers. Results show computer-based age estimation is nearly as reliable as human estimation.

Area of Science:

  • Computer Vision
  • Biometrics
  • Machine Learning

Background:

  • Automatic age estimation from facial images is a challenging task with applications in various fields.
  • Developing robust classifiers requires effective facial appearance modeling and accurate parameter extraction.

Purpose of the Study:

  • To quantitatively evaluate the performance of different classifiers for automatic age estimation.
  • To develop a statistical model of facial appearance for parametric image representation.
  • To compare the accuracy of machine-based age estimation with human performance.

Main Methods:

  • Generation of a statistical model of facial appearance.
  • Development of a compact parametric representation for face images.
  • Testing of quadratic function-based, shortest distance, and artificial neural network classifiers.

Related Experiment Videos

  • Implementation of age-specific and appearance-specific age estimation methods.
  • Selection of the most appropriate classifier for specific age ranges or subject clusters.

    • Main Results:

    • Different classifiers were quantitatively evaluated for their performance in automatic age estimation.
    • The model-based representation enabled classifiers to estimate age from unseen face images.
    • Age-specific and appearance-specific methods improved estimation accuracy by selecting tailored classifiers.
    • Computer-based age estimation achieved performance comparable to human estimators.

    Conclusions:

    • The developed statistical facial appearance model and tested classifiers provide a viable approach for automatic age estimation.
    • Machine learning algorithms, particularly when adapted for specific age groups or appearance types, can achieve high accuracy in age estimation.
    • The study demonstrates that computational methods are approaching human-level reliability in facial age estimation.