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

Automatic age estimation based on facial aging patterns.

Xin Geng1, Zhi-Hua Zhou, Kate Smith-Miles

  • 1School of Engineering and Information Technology, Deakin University, Australia. xge@deakin.edu.au

IEEE Transactions on Pattern Analysis and Machine Intelligence
|October 16, 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

Fixing Pillar[5]Arene-Based Rotaxanes Into Epoxy Networks to Produce Toughened Epoxy Resins.

Angewandte Chemie (International ed. in English)·2026
Same author

Stochastic Approximation Approaches to Group Distributionally Robust Optimization and Beyond.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

Transcriptomic and proteomic insights into the molecular mechanism underlying cell wall biosynthesis in Moso bamboo (Phyllostachys edulis).

Plant cell reports·2026
Same author

PAGD: the Persea americana Genome Database and a Docker-based transcriptome analysis workflow.

BMC genomics·2026
Same author

Causal effects of plasma protein-protein ratios on lung cancer subtypes: A proteome-wide Mendelian randomization and mediation analysis.

Medicine·2026
Same author

Sub-kHz linewidth, low noise single-frequency fiber laser based on Yb<sup>3+</sup>-doped fluoro-sulfo-phosphate fiber and self-injection locking.

Optics express·2026
Same journal

HardFlow: Hard-Constrained Sampling for Flow-Matching Models Via Trajectory Optimization.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Industrial Brain: Self-Evolving Neuro-Symbolic Autonomy with Causal Resilience for Cyber-Physical Systems.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Adaptive Hardness-Driven Dictionary Distillation for Incomplete Streaming View Clustering.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Achieving Text-based Person Retrieval with Any Granularity.

IEEE transactions on pattern analysis and machine intelligence·2026
See all related articles

This study introduces AGES (AGing pattErn Subspace), a novel method for automatic age estimation. AGES models facial aging patterns, achieving performance comparable to human observers and outperforming existing algorithms.

Area of Science:

  • Computer Vision
  • Biometrics
  • Machine Learning

Background:

  • Facial recognition studies extensively cover identity, expression, and gender, but automatic age estimation remains underexplored.
  • Aging variation presents unique challenges for accurate facial age estimation.
  • Existing age estimation methods are limited in scope and performance.

Purpose of the Study:

  • To propose and evaluate AGES (AGing pattErn Subspace), a novel automatic age estimation method.
  • To model the aging pattern of individuals using a representative subspace.
  • To compare AGES performance against existing methods and human perception.

Main Methods:

  • AGES models aging patterns by constructing a representative subspace from time-ordered facial images of individuals.

Related Experiment Videos

  • Age is estimated by projecting new facial images onto the subspace, minimizing reconstruction error.
  • AGES variants were compared with WAS, AAS, kNN, BP, C4.5, and SVM algorithms.

    • Main Results:

    • The proposed AGES method significantly outperformed all compared algorithms in age estimation accuracy.
    • AGES demonstrated performance comparable to human observers in age estimation tasks.
    • AGES variants also showed superior performance compared to baseline and established classification methods.

    Conclusions:

    • AGES offers a robust and effective approach to automatic age estimation by modeling aging patterns.
    • The method achieves human-level accuracy, indicating its potential for real-world applications.
    • AGES represents a significant advancement in the field of facial age estimation.