ML Anthology

Least Squares Congealing for Unsupervised Alignment of Images

Mark Cox, Sridha Sridharan, Simon Lucey, Jeffrey F. Cohn
CVPR 2008
doi:10.1109/CVPR.2008.4587573 /cvpr/2008/cox2008cvpr-least/

Abstract

In this paper, we present an approach we refer to as "least squares congealing" which provides a solution to the problem of aligning an ensemble of images in an unsupervised manner. Our approach circumvents many of the limitations existing in the canonical "congealing" algorithm. Specifically, we present an algorithm that:- (i) is able to simultaneously, rather than sequentially, estimate warp parameter updates, (ii) exhibits fast convergence and (iii) requires no pre-defined step size. We present alignment results which show an improvement in performance for the removal of unwanted spatial variation when compared with the related work of Learned-Miller on two datasets, the MNIST hand written digit database and the MultiPIE face database.

PDF CVPR Semantic Scholar

Cite

Text

Cox et al. "Least Squares Congealing for Unsupervised Alignment of Images." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2008. doi:10.1109/CVPR.2008.4587573

Markdown

[Cox et al. "Least Squares Congealing for Unsupervised Alignment of Images." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2008.](https://mlanthology.org/cvpr/2008/cox2008cvpr-least/) doi:10.1109/CVPR.2008.4587573

BibTeX

@inproceedings{cox2008cvpr-least,
  title     = {{Least Squares Congealing for Unsupervised Alignment of Images}},
  author    = {Cox, Mark and Sridharan, Sridha and Lucey, Simon and Cohn, Jeffrey F.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2008},
  doi       = {10.1109/CVPR.2008.4587573},
  url       = {https://mlanthology.org/cvpr/2008/cox2008cvpr-least/}
}