AAM Tracking

AAM Tracking is Active Appearance Model Face Tracker using OpenCV.  It is a library that was made by Dr. Radhika Vathsan as a way to track a face from a camera.

There are several examples of this used to control a 2d image, such as the youtube video below.

I am in the process of researching and looking into this code to see if it is possible to make this work with a 3d model.

http://www.youtube.com/watch?v=eSS4GFIH94w

Face Deformation with OpenGL

While doing research on some possible way to control a 3D face with OpenGL, i found this paper (http://paper.ijcsns.org/07_book/200704/20070420.pdf) named "3D Face Deformation Using Control Points and Vector Muscles" which was published on the International Journal of Computer Science and Network Security.

This paper provides information about a method of deforming a 3d face by using control points and vector muscles.

During my reading of this i have thought about actually using control points as a base point to control a 3D face while reading data from the users face. This should allow for a 3D face to appear to convey the same emotions as the user


I have not yet seen if a kinect or a webcam would either suit this method or which one would be better to use.

NB. All information used from this paper will be quoted and acknowledged 

Preliminary Ideas

There are a few idea i have thought about regarding Anonymity, these are

1. Using the Microsoft Kinect to help generate a complete 3D avatar which takes over as the user during a online video conference
2. Using a webcam or a Microsoft Kinect to make a 2d avatar's face as an overlay on top of the users face. This would involve no other alterations to the video except the users face would now be replaced
3. Using a webcam or a Microsoft Kinect to place a 2d avatar's face as an overlay again, however the video is replace by a premade 3d base head in a 3d modelling program. In this way the 3d base head will always be the same and only the 2d face would change. This would ensure that the user would be fully anonimised

The Thesis

This is my thesis topic for 2012 at the University of Sydney. There are several reasons why anonymity would we used while conversing over the internet and this thesis is to explore the possible ways in which this can be done with either a Microsoft Kinect or a ordinary webcam found on most computers in this day and age.

However simple versions of anonymity like blurring, while it would work would not be able to convey any emotion over the internet and other avenues need to be looked at for different circumstances.