Nonlinear Shape-Texture Manifold Learning

Xiaokan WANG  Xia MAO  Catalin-Daniel CALEANU  

IEICE TRANSACTIONS on Information and Systems   Vol.E93-D   No.7   pp.2016-2019
Publication Date: 2010/07/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.E93.D.2016
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)>>
Buy this Article

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.