The project I most enjoyed is my undergraduate individual project with supervisor Dr Tilo Burghardt from University of Bristol.
1. Motivation
A project carried out at Cardiff University captures the motion of a human’s face and produces a sequence of 48 spatio-temporal models per second using 3dMDFaceTM Dynamic System [1]. But those facial scans are really noisy and around 10TB are required for a 10mins video. In order to merge them into a single representation and improve their quality, semantically identical facial elements should be associated between the modes.
2. Related Work
1. Accurate registration based on symmetry plane around nose
[X.M Tang, J.S. Chen and Y.S Moon. Accurate 3D face
registration based on the symmetry plane analysis of nose region. 2008]
2. Real-time Face Pose Estimation
[Michael D.Breinstein, Daniel Kuettel, Thibaut Weise, Luc
Van Goolm Hanspeter Pfister. Real-time Face Pose Estimation from Single Range
Images. [2008]
3. Constructing a realistic Face Model of An Individual for
Expression Animation
[Yu Zhang, Edmond C. Prakash and Eric Sung. Constructing
a realistic Face Model of An
3. Outline of the Application
That project is able to resolve the approximate position of key features from a facial points cloud.
It is robust in terms of:
1. Scaling
2. Rotation
3. Translation
4. Noise
It is achieved in four stages as shown below:
 |
| Figure 1: Outline of the Application |
4. Plane Initialisation
Initialise a plane that is approximately aligned with the face. Find a few peripheral points and used then to find an amount of backwards-pointing vectors. The initial plane passes through the centre of gravity and its normal is the average of those vectors.
 |
| Figure 2: Calculation of a backwards pointing vector |
5. Iterative Algorithm
An iterative Algorithm with three degrees of freedom is used to find the bilateral symmetry axis of the face.
The iterative algorithm has 3 sub-iterations; each one serves a
degree of freedom:
1. Rotation of
the plane around its normal.
2. Shifting the
plane left and right.
3. Rotation of
the plane around the symmetry axis.
During each iteration the mirror difference is calculated.
 |
Figure 3: Mirror Difference of the face, P is an array with
sorted points
that lie on the plane that is aligned with the face
|
During each sub-iteration, the mirror difference (A2, A3 and
A4) is calculated for input values B2, B3 and B4. After each sub-iteration, the algorithm divides its
observation field and repeats until the observation field become too small to
be divided again.
 |
| Figure 4: How the observation
field is halved during each iteration |
The sub-iterations run the one after the other. Once they
all converge, the system runs them again and repeats until no changes are
observed.
6. Posing a Template
By posing a template the plane is rotated in another degree of freedom and the actual facial part is detected.
 |
| Figure 5: Comparison with pre-computed reference of range images,
using an Error Function |
7. Detection of Key Points:
Once the face is aligned, the approximate position of key Points are detected using curvature analysis and outward projection of points.
8. Evaluation:
The following image shows the evaluation of the program:
 |
| Figure 8: Initial Invariance |
 |
| Figure 9: Symmetry axis |
 |
| Figure 10: Range Images |
 |
| Figure 11: Key Points |
9. Future Work
Once the features of interest are found:
1. Polymesh
sequences can be merged into a single representation
2. Mesh quality
can be improved and
3. Their motion
can be driven by another model.
The facial registration system is also a useful tool in
expression analysis and face recognition systems.
10. Related Links
Poster: https://www.dropbox.com/s/md6c3r7rv4rjhd7/undegraduatePoster.pdfFull Thesis: https://www.dropbox.com/s/0znaz8x7msc77wj/udegraduateThesis.pdf
No comments:
Post a Comment