By using this site, you agree to our Privacy Policy and our Terms of Use. Close

Forums - Microsoft - Consumer Reports debunks the 'racist' Kinect

Here's an article from Consumer Reports in which they claim to debunk the rumors of Kinect having problems because of skin tone.

 

http://blogs.consumerreports.org/electronics/2010/11/consumer-reports-tests-kinect-facial-recognition-problems-video.html

November 4, 2010 Consumer Reports debunks the 'racist' Kinect

Is Kinect "Racist"?
Video: Consumer Reports

Shortly after the first Microsoft Kinect for Xbox reviews starting appearing in the wee hours last night, another Kinect story cropped up. It seems some testers encountered difficulty in getting the Kinect to identify players with darker skin color.

According to GameSpot:

[Our] testing suggests facial recognition features of Microsoft's motion-sensing camera system might not work properly for some gamers... In testing the Kinect, two dark-skinned GameSpot employees had problems getting the system's facial recognition features to work."

Consumer Reports did not encounter this issue with the Kinect and facial recognition when we first tested it. But it did remind of us a similar rumor about a "racist" HP laptop—which we debunked—last year. So we decided to test again the Microsoft Kinect with two players of different skin tones, in varying light levels.

Here's what we found: The log-in problem is related to low-level lighting and not directly to players' skin color. Like the HP webcam, 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.

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. 

This problem didn't prevent anyone who was affected from playing Kinect games, since it can "see" and track players' bodies and motions using a built-in infrared lighting system.

Take a look at our video to see how we tested and hear the full results.

(More at the link)



Around the Network

nice find :)



 How our favorite systems are just like humans and sometimes have issues finding their special someone...

Xbox 360 wants to KinectPS3 wants to Move!  Why are both systems having such relationship problems?  The reason is they both become so infactuated with desire while watching the Wii as it waggles on by. They simply want what they can't have.

 Official member of the Xbox 360 Squad

A predict a quiet thread.



GOTY Contestants this year: Dead Space 2, Dark Souls, Tales of Graces f. Everything else can suck it.

yes..very quiet



 

 

Silly inanimate don't have feelings of love let alone hate of certain people.



Former something....

Around the Network

Give us all the solid proof you want. It doesn't matter. MS and Kinect hate them blacks.



So we are taking blogs as solid proof now?



Gamespot admitted in the article "However, Kinect had no problems identifying a third dark-skinned GameSpot employee, recognizing his face after a single calibration."   They also stated they don't know how wide spread this problem was . Why would they lie about this?



Vetteman94 said:

So we are taking blogs as solid proof now?


It's Consumer Reports which is pretty highly respected.  OF course there's nothing stopping GameSpot from releasing their own video showing their own testing methods if they wish to counter Consumer Reports' findings.  Also it's strange that given how many Kinects were sold that there hasn't been hundreds of videos from people on YouTube with the same complaint if GameSpot is right.



Legend11 said:
Vetteman94 said:

So we are taking blogs as solid proof now?


It's Consumer Reports which is pretty highly respected.  OF course there's nothing stopping GameSpot from releasing their own video showing their own testing methods if they wish to counter Consumer Reports' findings.  Also it's strange that given how many Kinects were sold that there hasn't been hundreds of videos from people on YouTube with the same complaint if GameSpot is right.

Well I understand that,  its just that in most cases when a blog seems to be used as evidence for anything it seems to be shot down rather quickly.  Where this was not. 

Plus Gamespot even mentioned that a third employee had no troubles with it and also mentioned they did not know how wide spread the problem was.  Despite how credible Consumer Reports is for most things, they arent your goto source for video game information, and are rarely even brought up in any discussion.  Are you suggesting that Gamespot was lying about this?