Active appearance models (AAMs) provide a framework for modeling the joint shape and texture of an image. An AAM is a compact representation of both factors in a conditionally linear model. However, the standard AAM framework does not handle images which have missing features, or allow modification of certain structures in the image while leaving neighboring ones undeformed. We introduce the layered active appearance model (LAAM), which allows for missing features, occlusion, substantial spatial rearrangement of features, and which provides a more general representation that extends the applicability of the active appearance model.
Layered active appearance models
Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 ; 2 ; 1097-1102 Vol. 2
2005-01-01
530254 byte
Conference paper
Electronic Resource
English
Layered Active Appearance Models
British Library Conference Proceedings | 2005
|Constrained active appearance models
IEEE | 2001
|Constrained Active Appearance Models
British Library Conference Proceedings | 2001
|Active Appearance Models Revisited
British Library Online Contents | 2004
|View-based active appearance models
British Library Online Contents | 2002
|