Active appearance model: Difference between revisions

Revision as of 20:12, 21 January 2008

Revision as of 20:36, 17 July 2008

Line 1:

An '''Active Appearance Model''' (AAM)''' is a [[Computercomputer Visionvision]] algorithm for matching a [[statistical model]] of object shape and appearance to a new image. They are built during a training phase. A set of images together with coordinates of landmarks, that appear in all of the images is provided by the training supervisor.

The approach is widely used for matching and tracking faces and for [[Medicalmedical Imageimage Interpretationinterpretation]].

The algorithm uses the difference between the current estimate of appearance and the target image to drive an [[Optimization (mathematics)|optimization]] process.

By taking advantage of the [[least squares]] techniques, it can match to new images very swiftly.

It is related to the [[Activeactive Shapeshape Modelmodel]].

==External links==