GameSpot testing suggests facial recognition features of motion-sensing camera system might not work properly for some gamers; Microsoft says lighting levels to blame.
Source: In testing the Kinect, two dark-skinned GameSpot employees had problems getting the system's facial recognition features to work.
What we heard: Part of Microsoft's $500 million marketing push for Kinect includes positioning it as an accessible entertainment device for all audiences. However, it may be more accessible to some than others.
While testing out the Kinect, two dark-skinned GameSpot employees experienced problems with the system's facial recognition abilities. The system recognized one employee inconsistently, while it was never able to properly identify the other despite repeated calibration attempts. However, Kinect had no problems identifying a third dark-skinned GameSpot employee, recognizing his face after a single calibration. Lighter-skinned employees were also consistently picked up on the first try.
Not all games make much use of Kinect's facial recognition features.
It's important to note that the problems were only experienced with the system's facial recognition feature and don't prevent users from playing Kinect games. Skeletal tracking, a primary means of controlling games with Kinect, appeared to work the same for all GameSpot employees.
The system's inability to recognize a user only means that he or she would need to sign in manually and some games' features may not work properly as a result. For example, when a second player joins in to Kinect Adventures during the title's drop-in, drop-out multiplayer, the system can't bring up that player's proper in-game avatar automatically if it can't identify the new user first.
If Kinect does have some technical issues related to users' pigmentation, it wouldn't be a first for recognition technology. Last holiday season, users of Hewlett-Packard computers with built-in webcams reported problems with a face-tracking feature.
HP blamed the problem on the webcam's technology, "standard algorithms that measure the difference in intensity of contrast between the eyes and the upper cheek and nose." It said the system could have problems "seeing" that contrast if there is insufficient foreground lighting.