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

Human expression recognition from motion using a radial basis function network architecture.

M Rosenblum1, Y Yacoob, L S Davis

  • 1Comput. Vision Lab., Maryland Univ., College Park, MD.

IEEE Transactions on Neural Networks
|January 1, 1996
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

De novo adamantinomatous craniopharyngioma with long-term pre-diagnostic imaging.

Neuro-Chirurgie·2023
Same author

Aminolevulinic Acid Photodynamic Therapy-Induced Erosive Pustular Dermatosis of the Scalp.

Dermatologic surgery : official publication for American Society for Dermatologic Surgery [et al.]·2021
Same author

Dynamical disentanglement in an analysis of oscillatory systems: an application to respiratory sinus arrhythmia.

Philosophical transactions. Series A, Mathematical, physical, and engineering sciences·2019
Same author

Drug repositioning in SLE: crowd-sourcing, literature-mining and Big Data analysis.

Lupus·2016
Same author

The epileptic thalamocortical network is a macroscopic self-sustained oscillator: evidence from frequency-locking experiments in rat brains.

Scientific reports·2015
Same author

Optimizing randomized trial designs to distinguish which subpopulations benefit from treatment.

Biometrika·2012
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

This study introduces a new radial basis function network to identify human expressions from facial movements. The system achieved high accuracy in recognizing smiles and surprise, demonstrating its effectiveness in expression analysis.

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Machine Learning

Background:

  • Facial expression recognition is crucial for human-computer interaction.
  • Current methods often struggle with dynamic facial motion patterns.

Purpose of the Study:

  • To develop a novel radial basis function network architecture for correlating facial motion with human expressions.
  • To implement a hierarchical approach for expression identification, facial feature motion determination, and motion direction recovery.

Main Methods:

  • A hierarchical radial basis function network was designed.
  • Individual networks were trained to recognize specific expressions like 'smile' and 'surprise' using subject sequence data.
  • The network's performance was evaluated on retention, extrapolation, and rejection capabilities.

Related Experiment Videos

Main Results:

  • The developed network achieved 88% accuracy for retention of learned expressions.
  • It demonstrated 88% accuracy for extrapolating to new instances of expressions.
  • The system showed 83% accuracy in rejecting non-target expressions.

Conclusions:

  • The proposed radial basis function network architecture effectively learns correlations between facial motion patterns and human expressions.
  • The hierarchical approach provides a robust framework for expression recognition.
  • The high success rates indicate the system's potential for real-world applications in human-computer interaction.