I am working on a project where I have to identify a bunch of different body types.
I am starting by using the microsoft kinect and the player note, to remove the background. I then pass the image through pipet and I get a general “mass”.
You can see the attached patch (no kinect needed - I saved sample pics).
The next step - and this is where I am stuck - is how to identify specific characteristics.
For starters, I want to tell how tall is a person. I don’t need specifics (i.e. 1.80m) but rather a way so I can compare between the users.
I know the way to do this is to check what is the highest red pixel and the lowest red pixel and identify the distance between them.