Constrained Active Appearance Models
Abstract
Active Appearance Models (AAMs) have been shown to be useful for interpreting images of deformable objects. Here we place the AAM matching algorithm in a statistical framework, allowing extra constraints to be applied. This enables the models to be combined with other methods of object location. We demonstrate how user interaction can be used to guide the search and give results of experiments showing the effect of constraints on the performance of model matching.
Cite
Text
Cootes and Taylor. "Constrained Active Appearance Models." IEEE/CVF International Conference on Computer Vision, 2001. doi:10.1109/ICCV.2001.10056Markdown
[Cootes and Taylor. "Constrained Active Appearance Models." IEEE/CVF International Conference on Computer Vision, 2001.](https://mlanthology.org/iccv/2001/cootes2001iccv-constrained/) doi:10.1109/ICCV.2001.10056BibTeX
@inproceedings{cootes2001iccv-constrained,
title = {{Constrained Active Appearance Models}},
author = {Cootes, Timothy F. and Taylor, Christopher J.},
booktitle = {IEEE/CVF International Conference on Computer Vision},
year = {2001},
pages = {748-754},
doi = {10.1109/ICCV.2001.10056},
url = {https://mlanthology.org/iccv/2001/cootes2001iccv-constrained/}
}