No. 

The idea is that your viewing experience is as normal as ever so we have checks to make sure you’re set up correctly - but a couple of things will help to make sure everything works as it should.

• Lighting: Your face should be well lit and without strong directional light.
• Glasses: Make sure they don’t have a strong reflection or hide your eyebrows and eyes.
• Facial hair: It should be light enough not to conceal mouth movements.

Our algorithms are trained on our data sets of individually annotated frames that are representative of images encountered in a real test scenario - what we call 'in the wild'. By using our own data sets collected in the wild, we can maximize the chances that the algorithms will be able to read faces even in difficult situations: bad quality images (or cameras); when the lighting is bad; parts of the face are very shadowed or hidden; when people are either too far or too close to the camera; when they're wearing large/thick glasses; or even have a lot of facial hair. By being trained on 'wild' data the algorithm will perform more reliably 'in the wild' than it would otherwise.

Additionally, we enforce strict quality filters to ensure we only include the data for high quality sessions in the final data set. If occlusions or movement away from the camera interfere with the quality of the recording, the session is excluded. 

We only collect natural, authentic, 'in-the-wild' emotional responses. Because of this, not all recorded sessions will be good enough for a reliable emotions reading, for a variety of reasons – people moving out of the frame, or covering their face, for example.

We therefore enforce strict quality filters to ensure we only include the data for high quality sessions in the final data set. We generally see that about 15-25% of the total collected sessions are excluded from analysis due to poor lighting or other interferences.