FaceReader automatically analyzes a selection of 20 commonly used Action Units, such as raising of cheeks, wrinkling of nose, dimpling, and lip tightening. Action Units are the actions of individual muscles or groups of muscles. When an action is active, its intensity is displayed in 5 categories A (Trace), B (Slight), C (Pronounced), D (Severe), E (Max). Output will be presented to you on this scale with different colors and can be exported for further analysis in Excel, The Observer XT, or another program of your choice.
Export in detailed log as numerical values is possible, as well as export in real-time, using the FaceReader API, allowing you to create adaptive applications driven by facial action units. This module offers you valuable information in a minimal amount of time. Especially when you are analyzing a large amount of video recordings, this module will help you advance your research.
Create custom expressions
With the release of FaceReader 8, you can define your own algorithms and create custom expressions! Find out if your test participants show fake or genuine smiles for example, or define other affective attitudes, like pride, workload, pain, or embarrassment, by combining variables such as basic facial expressions, Action Units, and heart rate. You can even share these custom expressions with your fellow researchers.
Curious what Action Units actually look like? We have listed the 20 Action Units offered in the most recent version of FaceReader, of which you see three examples below, as well as some frequently occurring or difficult action unit combinations.
FaceReader analyzes left and right Action Units separately. This unique feature distinguishes the intensity of the active muscles at the left and the right side of the face. This is extremely interesting for research related to paralysis, muscular dystrophy, and more.
Contact us for more information! Our sales representatives are happy to provide you with 'Validation Action Unit Module' (by Tim den Uyl). This document presents a validation of the FaceReader Action Unit Module by evaluating the performance on an annotated dataset. It provides the agreement between FaceReader classifications and the coded dataset, as well as an evaluation of the performance of the individual AU classifiers.
FaceReader methodology white paper
Request the FREE FaceReader methodology note to learn more about facial expression analysis theory.
- Learn what FaceReader is and how it works
- Learn how the calibration works
- Get insight in quality of analysis and output