Knowledge Base

Sample Projects

You can download two example projects from your MyNoldus account: https://my.noldus.com

Sample Project - Two Stimuli

Five test participants watch two videos, one with baby twins that feed each other and one in which strange food is being prepared. Compare the facial expressions of the test participants while watching the two videos.

Sample Project - Infrared Recording

In this sample project we filmed a driver in a car driving in the near-dark to illustrate that FaceReader can analyze infrared recordings. In this project you can see what head rotations FaceReader can deal with. You can visualize Head orientation, Head position and Gaze angle.

Read the PDF file Description of FaceReader 10 sample projects, to see all the features that you can view in the projects. You can download this PDF file from the MyNoldus portal on the Noldus website (my.noldus.com).

Limitations Of The Current Version

The current FaceReader version has a number of limitations. It is good to keep these in mind when you start working with FaceReader.

• Glasses may hinder classification. Especially thick and dark frames can reduce performance significantly. It may be useful to have a number of rimless reading glasses available in a few strengths when you carry out a test. A polarization filter on the camera can help to avoid reflections in the glasses.
• Pose, movement and rotation of the test person are limited. The test person should stand or sit and look frontally into the camera (angle < 30°). That means that you should sit opposite of the test participant and not next to him/her if you want to ask questions during the test. In a social interaction setting (medical student - patient or consultant-client interaction) you would ideally position the camera on the conversation partner's shoulder. With this set-up people look almost straight into the camera when they talk to their partner. In practice this may not be possible but if you put the camera a short distance away, at the same height, with direct sight line to the participant's face, you have a working solution.

  In a consumer study you can use a cup or bowl holder so the dish is closer to the face and the test participant does not need to tilt his/her head downwards.

  If your test participants need to read instructions or fill in a questionnaire, you can present this information on a screen and attach the camera to the screen.

• FaceReader requires strict light conditions. See Lighting Setup.

  You can use (near) infrared light with a camera that is sensitive for this type of light. FaceReader 10 supports (near) infrared recordings. Please note that it is not possible to measure heart rate, heart rate variability and respiratory rate with infrared recordings.

• Factors that partially hide the face, like a hat, hair that covers the forehead, or very heavy facial hair may hinder the analysis.

  Hands in front of the face should also be avoided. You may normally offer your test participants something to eat or drink during the test to make them feel more comfortable. However, when eating or drinking the test participant blocks part of the face with his/her hand and the cup/glass/cutlery. Make sure the test participant finishes his/her cup of coffee before you start the test unless, of course, the purpose of the test is to see the reaction to a new food product or beverage.

  Some people have the natural tendency to touch their face without realizing it. You may want to warn your test participant to keep their arms on the table throughout the test in order to get the best possible results.

• With the base functionality of FaceReader can analyze one face at once. If there are more faces in an image, you can select one of the faces by dragging the borders in the preview window and analyze that face. Then do the same with the other faces. Of course, the positions of the faces must not change significantly. See also the notes in Analyze Facial Expressions.

  If your FaceReader license included the Advanced Research Module you can analyze up to eight faces in a video simultaneously. See The Advanced Research Module.

• For FaceReader to analyze facial expressions, emotions must be visible in the face. "All my test participants looked neutral throughout the test" is an often heard complaint. It may help to test people in their natural environment, at home or in another familiar environment (restaurant, school, office, etc.). Running your tests in the test facilities in your office has the obvious advantage that you can control the test conditions much better than out in the field. The downside, however, is that people may react differently to your stimuli or not at all.
• Please contact us if any of the limitations above impede your research.

Improving FaceReader's Performance

The following tips to improve FaceReader's performance apply to all analyses done in FaceReader and are especially important when using batch analysis of videos.

• Length of videos - Although there are no built-in limitations regarding the length of videos, it is good to keep in mind that the longer the video, the more data needs to be saved in the computer's internal memory. Data is only saved to the hard disk after every analysis. We recommend to use videos that have a maximum duration of two hours (if 15 fps) or one hour (if 30 fps).
• Resolution of videos - Higher resolution does not mean better facial expression analysis with FaceReader. High resolutions are scaled down to a maximum of 1280x1280 pixels while keeping the original video aspect ratio. Keep in mind that the scaling costs processing power and other resources which do have an influence on the performance. The minimum video resolution is 640x480.
• Analysis options - In the FaceReader Settings you can select what optional classifications you want to analyze. Select only those options that you need. Selecting more options requires more processor capacity.
• Visualizations - Graphical presentations cost a huge amount of processing power and other resources (e.g. memory). For best performance you can best close the visualizations during analysis.
• Processing unit - A powerful processor and sufficient internal memory is a prerequisite. Please see the System Requirements.
• Applications running in the background - Make sure that no other applications are running.
• Test real products - You can show test participants pictures of your product, videos/commercials featuring your product, or you can give them the real product. Generally real products elicit greater responses. While having the real product to view is preferable to seeing a photo, real-life use is even more preferred. So, if you want to know whether your test participants like your new healthy flour mix, for example, you can ask them to bake pancakes in a test kitchen, and observe the displayed reactions during the baking process and the consumption phase.
• Present more than one stimulus - If you want to test your new product (commercial, beverage, etc.) it is best to embed it in a series of other products. In this way the test participants do not concentrate fully on the focus product and will respond in a more natural way. This also allows the participants to compare your product with similar ones. Be sure to randomize the order in which you present the products.

Mouse Control

Some features of FaceReader are controlled with mouse clicks. If you do not have a mouse, you can use a mouse-emulator like NeatMouse to use those FaceReader functions. You can download NeatMouse for free.

http://neatdecisions.com/products/neatmouse/

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