For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Nonlinear Shape-Texture Manifold Learning
Xiaokan WANG Xia MAO Catalin-Daniel CALEANU
IEICE TRANSACTIONS on Information and Systems
Publication Date: 2010/07/01
Online ISSN: 1745-1361
Print ISSN: 0916-8532
Type of Manuscript: LETTER
Category: Image Recognition, Computer Vision
manifold learning, shape-texture manifold, local linear embedded,
Full Text: PDF(1.3MB)>>
For improving the nonlinear alignment performance of Active Appearance Models (AAM), we apply a variant of the nonlinear manifold learning algorithm, Local Linear Embedded, to model shape-texture manifold. Experiments show that our method maintains a lower alignment residual to some small scale movements compared with traditional AAM based on Principal Component Analysis (PCA) and makes a successful alignment to large scale motions when PCA-AAM failed.