Active Shape Models
Active Shape Models are statistical models of the shapes of objects
which iteratively deform to fit to an example of the object in a new
image. The shapes are constrained by a
Statistical Shape Model
to vary only in ways seen in a training set of labelled examples.
In addition to the shape model, we require models of the image appearance
around each model point. The simplest is to assume the points lie on
strong edges. More complex models can be built to represent the statistical
variation of the gradient along profiles through the points, normal to the
boundary curve at that point.
We assume we have an initial estimate for the pose and shape parameters
(eg the mean shape). This is iteratively updated as follows:
 Look along normals through each model point to find the best local match
for the model of the image appearance at that point (eg strongest nearby
edge)
 Update the pose and shape parameters to best fit the model instance to
the found points
 Repeat until convergence
The performance can be significantly improved using a multiresolution
implementation, in which we start searching on a coarse level of a
gaussian image pyramid, and progressively refine. This leads to much
faster, more accurate and more robust search.
Face Example
Example of a multiresolution search (displayed at highest resolution):



Initial Pose 
After 5 iterations 
Convergence 
This takes less than one second on a Sun Sparc20.
A detailed report about Active Shape Models and Active Appearance Models
Postscript (>1.6Mb)
You can now download a set of tools to build and play with
Appearance Models and AAMs here. Enjoy.
Tim Cootes