Title :
Active appearance models
Author :
Cootes, Timothy F. ; Edwards, Gareth J. ; Taylor, Christopher J.
Author_Institution :
Div. of Imaging Sci. & Biomed. Eng., Manchester Univ., UK
fDate :
6/1/2001 12:00:00 AM
Abstract :
We describe a new method of matching statistical models of appearance to images. A set of model parameters control modes of shape and gray-level variation learned from a training set. We construct an efficient iterative matching algorithm by learning the relationship between perturbations in the model parameters and the induced image errors
Keywords :
image matching; image texture; iterative methods; learning (artificial intelligence); optimisation; statistical analysis; active appearance models; deformable template; gray-level variation; iterative method; learning; model matching; optimisation; shape matching; statistical models; texture matching; Active shape model; Deformable models; Image generation; Image reconstruction; Image segmentation; Iterative algorithms; Optimization methods; Robustness; Shape control; Surface fitting;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
