Knowledge Base

Introduction

Main Topics

• How to use this Help?
• An introduction to FaceReader
• How does FaceReader work?
• Sample projects
• Limitations of the current version
• Modules
• What is new in FaceReader 10

How to Use This Help?

TIPS

• If you do not see the Table of Contents on the left, enlarge the Help window or zoom out the characters (Ctrl+mouse wheel, or Ctrl+-).
• To search for two or more adjacent words, use quotes, for example "Action Unit".
• To go back to the search results after visiting one of the result pages, click again on the magnifying glass icon in the Search field.

An Introduction to FaceReader

Six Basic Expressions

FaceReader is a program for facial expression analysis. It can detect emotional expressions in the face. It can identify six basic expressions:

• Happy
• Sad
• Angry
• Surprised
• Scared
• Disgusted
• A Neutral state

Contempt

In addition to the six basic expressions, FaceReader can detect contempt. Contempt is an expression in which one corner of the lips is tightened and slightly raised.

Baby FaceReader

Baby FaceReader is a special version of FaceReader. It has been developed for babies and infants from 6-24 months old. Please note that Baby FaceReader analyzes Action Units, Valence and Arousal, it cannot detect the basic facial expressions. Baby FaceReader is based on the Baby FACS developed by Oster. Valence calculation in Baby FaceReader is based on Action Unit 6, 12 and 25 for positive valence. It takes the average intensity of these Action Units. Activity of Action Unit 1, 4, 7, 20, 25 and 43 results in a negative valence value.

Your Baby FaceReader license can be extended with the Vital Signs Module. Baby FaceReader cannot be combined with other modules. The Voice Analysis Module, the Advanced Research Module and the Consumption Behavior Module are not available with Baby FaceReader.

References

Messinger, D.S., Mahoor, M.H., Chow, S.M. & Cohn, J.F. (2009). Automated measurement of facial expression in infant-mother interaction: A pilot study. Infancy 14(3): 285-305.

Oster, H. 2003. Baby FACS: Facial Action Coding System for Infants and Young Children. Unpublished monograph and coding manual. New York University.

Oster, H. 2012. The repertoire of infant facial expressions: An ontogenetic perspective. DOI: 10.1093/acprof:oso/9780198528845.003.0010.

Rosenstein, D. & Oster, H. (1988). Differential facial responses to four basic tastes in newborns. Child development 59(6): 1555-1568.

Webb, R., Ayers, S. & Endress, A. (2018). The City Infant Faces Database: A validated set of infant facial expressions. Behavior Research Methods 50: 151-159.

Additional Classifications

FaceReader can also analyze:

• Facial states — Left and right eye open or closed, mouth open or closed and eyebrows raised, neutral or lowered
• Global gaze direction — The gaze direction of the eyes, to the left, left-up and left-down, to the right, right-up and right-down and straight forward, up and down.
• Gaze Type — Fixation or saccade.
• Gaze angles — Horizontal and vertical gaze angle (in degrees).
• Gaze location — The participant's gaze location on the screen/stimulus. This option is available with the Advanced Research Module.
• Head orientation — The orientation of the head (pitch, yaw and roll, in degrees deviating from looking straight forward).
• Head position — Horizontal, vertical and depth position relative to the camera.
• Valence — Which indicates whether the person's emotional status is positive, negative or neutral.
• Arousal — Which indicates how active the person is.
• Subject characteristics — The estimation of the test participant's gender and age, and whether the person is wearing glasses or not. Subject characteristics are not available in Baby FaceReader.
• Action Units — FaceReader can analyze the 20 most common Action Units in the face. In addition, there are a number of Action Units available as Custom Expressions. FaceReader analyzes Action Units in the left and right part of the face. Action Units are available with the Action Unit Module. For Baby FaceReader you do not need the Action Unit Module as extra module. Action Unit analysis is an integral part of Baby FaceReader.
  See The Action Unit Module
• Custom expressions — FaceReader comes with a library of expressions like Interest, Attention, Confusion and Boredom. It is also possible to define your own Custom Expressions, based on Action Units, facial expressions, valence, arousal, and other parameters. Custom Expressions are available with the Action Unit Module.
• Vital signs — This option is available with the Vital Signs Module. FaceReader can estimate the test participant's heart rate and heart rate variability and respiratory (breathing) rate from the camera or video images of their face.
  See The Vital Signs Module
• Expressions in the voice — This option is available with the Voice Analysis Module. FaceReader can detect Neutral, Happy, Sad and Angry in the participant's voice.
• Consumption Behavior — This option is available with the Consumption Behavior Module. FaceReader can analyze chewing behavior and count the number of intake events (bites/sips). Consumption Behavior analysis is not available in Baby FaceReader.
  See The Consumption Behavior Module

FaceReader and The Observer XT

FaceReader data can be imported into The Observer XT, the leading software package for the collection, analysis and presentation of observational data. This enables you to integrate FaceReader data with other data, such as manually logged events, physiological data and eye tracker data and to analyze the full context. For instance, what is the test participant watching on the screen and what emotion does that trigger.

FaceReader can be used in a wide range of research areas:

• Psychology — How do people respond to particular stimuli, e.g. in cognitive research.
• Education — Observing students' facial expressions can support the development of educational tools.
• Human-computer interaction — Facial expressions can provide valuable information about user experience.
• Usability testing — Emotional expressions can indicate the ease of use and efficiency of user interfaces.
• Market research — How do people respond to a new commercial's design?
• Consumer behavior — How do participants in a sensory panel react to a new product?

Source: FaceReader 10 Reference Manual (Help), Noldus Information Technology