Determining Correspondences for Statistical Models of Appearance
Abstract
In order to build a statistical model of appearance we require a set of images, each with a consistent set of landmarks. We address the problem of automatically placing a set of landmarks to define the correspondences across an image set. We can estimate correspondences between any pair of images by locating salient points on one and finding their corresponding position in the second. However, we wish to determine a globally consistent set of correspondences across all the images. We present an iterative scheme in which these pair-wise correspondences are used to determine a global correspondence across the entire set. We show results on several training sets, and demonstrate that an Appearance Model trained on the correspondences can be of higher quality than one built from hand marked images.
Cite
Text
Walker et al. "Determining Correspondences for Statistical Models of Appearance." European Conference on Computer Vision, 2000. doi:10.1007/3-540-45054-8_54Markdown
[Walker et al. "Determining Correspondences for Statistical Models of Appearance." European Conference on Computer Vision, 2000.](https://mlanthology.org/eccv/2000/walker2000eccv-determining/) doi:10.1007/3-540-45054-8_54BibTeX
@inproceedings{walker2000eccv-determining,
title = {{Determining Correspondences for Statistical Models of Appearance}},
author = {Walker, Kevin N. and Cootes, Timothy F. and Taylor, Christopher J.},
booktitle = {European Conference on Computer Vision},
year = {2000},
pages = {829-843},
doi = {10.1007/3-540-45054-8_54},
url = {https://mlanthology.org/eccv/2000/walker2000eccv-determining/}
}