Bidirectional Warping of Active Appearance Model
Abstract
Active Appearance Model (AAM) is a commonly used method for facial image analysis with applications in face identification and facial expression recognition. This paper proposes a new approach based on image alignment for AAM fitting called bidirectional warping. Previous approaches warp either the input image or the appearance template. We propose to warp both the input image, using incremental update by an affine transformation, and the appearance template, using an inverse compositional approach. Our experimental results on Multi-PIE face database show that the bidirectional approach outperforms state-of-the-art inverse compositional fitting approaches in extracting landmark points of faces with shape and pose variations.
Cite
Text
Mollahosseini and Mahoor. "Bidirectional Warping of Active Appearance Model." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2013. doi:10.1109/CVPRW.2013.129Markdown
[Mollahosseini and Mahoor. "Bidirectional Warping of Active Appearance Model." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2013.](https://mlanthology.org/cvprw/2013/mollahosseini2013cvprw-bidirectional/) doi:10.1109/CVPRW.2013.129BibTeX
@inproceedings{mollahosseini2013cvprw-bidirectional,
title = {{Bidirectional Warping of Active Appearance Model}},
author = {Mollahosseini, Ali and Mahoor, Mohammad H.},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2013},
pages = {875-880},
doi = {10.1109/CVPRW.2013.129},
url = {https://mlanthology.org/cvprw/2013/mollahosseini2013cvprw-bidirectional/}
}