FaceReader

FaceReader is the world's first tool that is capable of automatically analyzing facial expressions, providing users with an objective assessment of a person’s emotion.

  • Save time and resources.
  • Increase accuracy and reliability.
  • Introduce objectivity in observations.
  • No calibration required.
  • Easy integration with The Observer® XT for analysis and visualization.
  • Real-time access to collected data allows other software to respond to emotions.
  • All ethnic groups can be analyzed.
  • Including analysis of children's faces.


The human face provides a number of signals essential for interpersonal communication. It is one of our most direct means of communication and allows us to recognize someone’s affective state and intentions. However, annotating facial expressions objectively can be a real challenge. FaceReader is the revolutionary tool that is capable of automatically analyzing facial expressions, providing users with an objective assessment of a person’s emotion.

Features
FaceReader is the first truly automated system for the recognition of a number of specific properties in facial images, including the following expressions:

  • happy
  • sad
  • angry
  • surprised
  • scared
  • disgusted
  • 'neutral' state


Work with FaceReader
FaceReader works in three steps: face finding, face modeling, and face classification.  You can work off-line using video, on-line for live analysis using a USB camera, and you can upload still images for analysis. With all three possibilities FaceReader generates data, which give you insight into the emotional expressions of the test participant.

When analyzing from video, you can choose an accurate frame-by-frame mode or skip frames for high-speed analysis. The best results are achieved with diffuse frontal lighting of the test participant; Noldus provides illumination for optimization of your set-up. You can follow the emotional expressions of your test participant if his orientation, movement, and rotation is within certain limits.

FaceReader can quickly detect interesting episodes, even in long series of events. The computer does the work for you! FaceReader includes a basic person algorithm, allowing subjects to be recognized after prior input of the original facial image. 

Visualization
FaceReader automatically analyzes facial expressions, which can be visualized as bar graphs, in a pie chart, and as a continuous signal. An additional gauge display summarizes the negativity or positivity of the emotion (valence). In addition to analyzing expressions, FaceReader can classify faces on the following properties: gender, age, ethnicity, and facial hair (beard and/or moustache). FaceReader can accurately read the faces of children who are 3 years or older. Although you can analyze all ethnic groups, FaceReader is currently not well-trained to work with children from East Asia or South-East Asia. The test database is still being expanded. Glasses can also interfere with the analysis process.

Using FaceReader with The Observer XT
Data acquired with FaceReader can be easily imported into The Observer XT, our software package for collection, analysis, and presentation of observational data. This offers a unique solution for synchronization, integration, and analysis of FaceReader data with other data, such as manually logged events, physiological data, keystrokes, mouse clicks, video and screen captures, eye tracking data, etc. This compatibility enables you to analyze the full context: what user interface is the test participant looking at or which image is triggering an emotion? Classifications can be exported to analytical and database programs such as Microsoft Access and Excel or (in plain text format) to any other preferred package.

Real-time access
Facial expressions detected by FaceReader can be accessed in real time by other applications, making the program an ideal tool for research on affective computing and the design of adaptive interfaces. In other words, it allows other software programs to respond instantaneously to the emotional state of the user.

Research areas

  • Psychology: How do people respond to particular stimuli, e.g. in fear 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 commercial’s new design?
  • Consumer behavior: How do participants in a sensory panel react to a stimulus?