Sciweavers

Share
CVPR
2008
IEEE

Local minima free Parameterized Appearance Models

13 years 1 months ago
Local minima free Parameterized Appearance Models
Parameterized Appearance Models (PAMs) (e.g. Eigentracking, Active Appearance Models, Morphable Models) are commonly used to model the appearance and shape variation of objects in images. While PAMs have numerous advantages relative to alternate approaches, they have at least two drawbacks. First, they are especially prone to local minima in the fitting process. Second, often few if any of the local minima of the cost function correspond to acceptable solutions. To solve these problems, this paper proposes a method to learn a cost function by explicitly optimizing that the local minima occur at and only at the places corresponding to the correct fitting parameters. To the best of our knowledge, this is the first paper to address the problem of learning a cost function to explicitly model local properties of the error surface to fit PAMs. Synthetic and real examples show improvement in alignment performance in comparison with traditional approaches.
Minh Hoai Nguyen, Fernando De la Torre
Added 12 Oct 2009
Updated 28 Oct 2009
Type Conference
Year 2008
Where CVPR
Authors Minh Hoai Nguyen, Fernando De la Torre
Comments (0)
books