A Novel Convergence Scheme for Active Appearance Models

Batur, Aziz Umit; Hayes, Monson H.

doi:10.1109/CVPR.2003.1211376

A Novel Convergence Scheme for Active Appearance Models

Aziz Umit Batur, Monson H. Hayes

CVPR 2003 pp. 359-368

doi:10.1109/CVPR.2003.1211376 /cvpr/2003/batur2003cvpr-novel/

Abstract

The active appearance model (AAM) algorithm is a powerful tool for modeling images of deformable objects. AAM combines a subspace-based deformable model of an object's appearance with a fast and robust method of fitting this model to a previously unseen image. The speed of this algorithm comes from the assumption that the gradient matrix is fixed around the optimal coefficients for all images. In this paper, we propose a convergence scheme for AAM that adapts this gradient matrix to the target image's texture during convergence by adding linear modes of change that are based on the texture eigenvectors of AAM. We show that this adaptive strategy for the gradient matrix provides a significant increase in the performance of the AAM algorithm.

CVPR Semantic Scholar

Cite

Text

Batur and Hayes. "A Novel Convergence Scheme for Active Appearance Models." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2003. doi:10.1109/CVPR.2003.1211376

Markdown

[Batur and Hayes. "A Novel Convergence Scheme for Active Appearance Models." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2003.](https://mlanthology.org/cvpr/2003/batur2003cvpr-novel/) doi:10.1109/CVPR.2003.1211376

BibTeX

@inproceedings{batur2003cvpr-novel,
  title     = {{A Novel Convergence Scheme for Active Appearance Models}},
  author    = {Batur, Aziz Umit and Hayes, Monson H.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2003},
  pages     = {359-368},
  doi       = {10.1109/CVPR.2003.1211376},
  url       = {https://mlanthology.org/cvpr/2003/batur2003cvpr-novel/}
}