Computer Expression Recognition Toolbox

@article{Bartlett2008ComputerER,
  title={Computer Expression Recognition Toolbox},
  author={Marian Stewart Bartlett and Gwen Littlewort and Tingfan Wu and Javier R. Movellan},
  journal={2008 8th IEEE International Conference on Automatic Face & Gesture Recognition},
  year={2008},
  pages={1-2}
}
We present a live demo of the Computer Expression Recognition Toolbox (CERT) developed at University of California, San Diego. CERT measures facial expressions in real-time, and codes them with respect to expressions of basic emotion, as well as over 20 facial actions from the Facial Action Coding System (Ekman & Friesen, 1978). Head pose (yaw, pitch, and roll) is also detected using an algorithm presented at this conference (Whitehill & Movellan, 2008). A sample output is shown in Figure 1. 

Figures, Results, and Topics from this paper.

Key Quantitative Results

  • Automated classifiers were able to differentiate real from fake pain significantly better than naïve human subjects, and to detect driver drowsiness above 98% accuracy.
  • Performances on a benchmark datasets (Cohn-Kanade) show state of the art performance for both recognition of basic emotions (98% correct detection for 1 vs all, and 93% correct for 7 alternative forced choice), and for recognizing facial actions from the Facial Action Coding System (mean .93 area under the ROC over 8 facial actions, equivalent to percent correct on a 2-alernative forced choice).

Explore Further: Topics Discussed in This Paper

Citations

Publications citing this paper.
SHOWING 1-10 OF 31 CITATIONS

Detecting Drivers' Mirror-Checking Actions and Its Application to Maneuver and Secondary Task Recognition

  • IEEE Transactions on Intelligent Transportation Systems
  • 2016
VIEW 10 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Human Behavior towards Virtual Humans

VIEW 7 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Analysis of driver behaviors during common tasks using frontal video camera and CAN-Bus information

  • 2011 IEEE International Conference on Multimedia and Expo
  • 2011
VIEW 5 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Study of Mechanisms of Social Interaction Stimulation in Autism Spectrum Disorder by Assisted Humanoid Robot

  • IEEE Transactions on Cognitive and Developmental Systems
  • 2018
VIEW 3 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

References

Publications referenced by this paper.
SHOWING 1-7 OF 7 REFERENCES

SmileMaze : A real - time program training in expression recognition

J. Tanaka, J. Movellan, M. Bartlett, J. Cockburn, M. Pierce
  • 2008
VIEW 1 EXCERPT

Automatic recognition of facial actions in spontaneous expressions

S. BartlettM., C. LittlewortG., +3 authors R. MovellanJ.
  • 2006

Robust real-time face detection

  • Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001
  • 2001

Comprehensive database for facial expression analysis

  • Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition (Cat. No. PR00580)
  • 2000