Title :
Layered active appearance models
Author :
Jones, Eagle ; Soatto, Stefano
Author_Institution :
Dept. of Comput. Sci., California Univ., Los Angeles, CA
Abstract :
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
Keywords :
feature extraction; image texture; feature substantial spatial rearrangement; image joint shape; image texture; layered active appearance model; linear model; missing feature; Active appearance model; Active shape model; Computer science; Computer vision; Eyes; Licenses; Mouth; Nose; Principal component analysis;
Conference_Titel :
Computer Vision, 2005. ICCV 2005. Tenth IEEE International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7695-2334-X
DOI :
10.1109/ICCV.2005.133