Observe > Understand > Communicate
Solutions for Behavioural Research
FaceReader
Overview
FaceReader automatically analyses facial expressions, providing an objective measurement of emotions. It classifies the six basic expressions: happy, sad, angry, surprised, scared and disgusted, as well as recognising 'contempt' and a 'neutral' state. Attitudes such as ‘interest’, ‘boredom’ and ‘confusion’ can also be automatically measured and recent work even allows researchers to explore whether a person is being sincere (for example when they smile).
FaceReader also logs: Action Units, valence, arousal, gaze direction, head orientation, facial states and custom expressions.
Free 14 day trial available to evaluate the software and support grant bids.
How it Works
Using still images, video clips or a live feed, FaceReader classifies the face through:
- Face Finding – automatically locates the face using a deep learning based face finding algorithm.
- Face Modelling – FaceReader uses a facial modelling technique based on deep neural networks. It synthesizes an artificial face model, which describes the location of almost 500 key points in the face.
- Face Classification – Classification of the facial expressions is done by a trained deep artificial neural network to recognize patterns in the face. FaceReader directly classifies the facial expressions from image pixels.
Features and Benefits
| Feature | Benefit | |
|---|---|---|
| Easy to use and automatic analysis | Saves time and gives clear insights into facial behaviour | |
| Project Action Module | Analyse group data and present stimuli using the Stimulus Presentation Tool | |
| Action Unit Module | Classifies the 20 most common action units for more subtle facial changes, and 3 affective attitudes: ‘interest’, ‘boredom’ and ‘confusion’ on an experimental basis | |
| RPPG Module | Estimates heart rate from colour changes in the skin, reflecting blood flow and oxygenation | |
| Wide variety of visualisation options | Data easily accessible to users | |
| Integrated with other data sources such as other behaviours, physiological measurements and eye tracking via The Observer XT | Part of a complete solution for your research needs | |
| Baby FaceReader | Since young infants are unable to provide verbal feedback, their facial expressions can give extra insights that help to understand their emotional reactions. |
Video
Scenarios
Here are some of the many scenarios which have used FaceReader:
- Psychologists
- Researching fear responses
- Market Research
- Testing the impact of new marketing material
- Education
- Developing more provocative and memorable study aids
- Human-computer interaction
- Examining the effectiveness of user interfaces