RI | Publications | Local Minima Free Parameterized Appearance Models

Text only version of this site

Local Minima Free Parameterized Appearance Models
M.H. Nguyen and F. De la Torre Frade
IEEE Conference on Computer Vision and Pattern Recognition, June, 2008.

Jump to: Abstract | Notes | Text Reference | BibTeX Reference

Abstract

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.

Notes

Note: the associated project is component analysis for data analysis and face group

Text Reference

M.H. Nguyen and F. De la Torre Frade, "Local Minima Free Parameterized Appearance Models," IEEE Conference on Computer Vision and Pattern Recognition, June, 2008.

BibTeX Reference

@inproceedings{Nguyen_2008_6039,
   author = "Minh Hoai Nguyen and Fernando De la Torre Frade",
   title = "Local Minima Free Parameterized Appearance Models",
   booktitle = "IEEE Conference on Computer Vision and Pattern Recognition",
   month = "June",
   year = "2008",
   note = "the associated project is component analysis for data analysis and face group"
}