Despite some claims that Kinect doesn't properly recognize dark-skinned users, Consumer Reports stated emphatically that its tests concluded that was bunk.
GameSpot published a feature on Wednesday which claimed that two dark-skinned employees had trouble with Kinect's facial recognition capabilities when logging in to use their avatar. The "skeletal tracking" of Kinect wasn't a problem and games could be played fine, but GameSpot claimed that the Kinect was often unable to identify users with dark complexions if they wanted to jump into a game in progress. Attempts to calibrate the system for the different complexions didn't yield results. In response, Microsoft said that after internal testing, it was confident that all ethnicities and complexions could use Kinect. Consumer Reports, often a watchdog for faulty products in any industry, released a report today that after extensive testing it found no evidence that Kinect worked differently for different ethnicities.
"While testing out the Kinect, two dark-skinned GameSpot employees experienced problems with the system's facial recognition abilities," GameSpot editor Brendan Sinclair wrote.
Microsoft told GameSpot that its claims were ridiculous. "The goal of Kinect is to break down the barriers for everyone to play, and it will work with people of all shapes and ethnicities at launch." In a later statement, Microsoft blamed the problems on proper lighting: "Kinect works with people of all skin tones. And just like a camera, optimal lighting is best. Anyone experiencing issues with facial recognition should adjust their lighting settings, as instructed in the Kinect Tuner."
Consumer Reports backed up Microsoft's claim. "The log-in problem is related to low-level lighting and not directly to players' skin color," wrote Carol Mangis for the Report (not to be confused with the other Report). "The Kinect camera needs enough light and contrast to determine features in a person's face before it can perform software recognition and log someone into the game console automatically."
The report went on: "Essentially, the Kinect recognized both players at light levels typically used in living rooms at night and failed to recognize both players when the lights were turned down lower. So far, we did not experience any instance where one player was recognized and the other wasn't under the same lighting conditions."
GameSpot plays the race card, and Microsoft and Consumer Reports pulls out the science. I'm sorry, GameSpot. I'm siding with science on this one.