Local minima free Parameterized Appearance Models

Parameterized appearance models (PAMs) (e.g. eigen-tracking, 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,...

Full description

Saved in:
Bibliographic Details
Published in:2008 IEEE Conference on Computer Vision and Pattern Recognition Vol. 2008; pp. 1 - 8
Main Authors: Minh Hoai Nguyen, De la Torre, Fernando
Format: Conference Proceeding Journal Article
Language:English
Published: United States IEEE 23.06.2008
Subjects:
Active appearance model
Active shape model
Computer errors
Cost function
Optimization methods
Principal component analysis
Robots
Surface fitting
Testing
Training data
ISBN:9781424422425, 1424422426
ISSN:1063-6919, 1063-6919, 2575-7075
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Parameterized appearance models (PAMs) (e.g. eigen-tracking, 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.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISBN:9781424422425
1424422426
ISSN:1063-6919
1063-6919
2575-7075
DOI:10.1109/CVPR.2008.4587524