Kinect Face Detection

Question

I want to do face detection using Microsoft Kinect, I can crop part of the RGB video and make a rectangle around the face in Skeleton View, but I can’t detect the RGB (normal image) of the face in WPF. How can i do this?

Answer 1

The good thing is that kinect identifies someone on the Xbox, that it accepts different characteristics of people's faces (using depth images), for example, I have a 1/2 inch nose, while you have 3/8 inch nose. This is determined by my depth from certain parts of the person’s face. Depth Calculation Algorithm (V1.0):

DepthImageFrame depthFrame short[] rawDepthData = new short[depthFrame.PixelDataLength]; depthFrame.CopyPixelDataTo(rawDepthData); int depth = rawDepthData[depthIndex] >> DepthImageFrame.PlayerIndexBitmaskWidth; 

Then you can say things like:

 if(depth > 500) { //do something } 

See Channel 9 for more depth information. Hope this helps!

Answer 2

Check out the new SDK (1.5), it has a Face Tracking Tool.

http://blogs.msdn.com/b/kinectforwindows/archive/2012/05/21/kinect-for-windows-runtime-and-sdk-version-1-5-released.aspx

http://www.microsoft.com/en-us/kinectforwindows/develop/learn.aspx

Answer 3

It is possible to use WPF, I used the "Skeleton head" position and create a frame, and then cut the image of this position from the RGB frame and paste it there. It works by the way, but needs some improvements. m tries to transfer this array of images to a neural network, and then map it. let's see how much i can do.

Thanks for helping u'r in any way.