Least Squares Congealing for Unsupervised Alignment of Images - Robotics Institute Carnegie Mellon University

Least Squares Congealing for Unsupervised Alignment of Images

Mark Cox, Simon Lucey, Sridha Sridharan, and Jeffrey Cohn
Conference Paper, Proceedings of (CVPR) Computer Vision and Pattern Recognition, June, 2008

Abstract

n this paper, we present an approach we refer to as ?east 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 ?ongealing?algorithm. Speci?cal ly, 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-de?ned 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.

BibTeX

@conference{Cox-2008-9988,
author = {Mark Cox and Simon Lucey and Sridha Sridharan and Jeffrey Cohn},
title = {Least Squares Congealing for Unsupervised Alignment of Images},
booktitle = {Proceedings of (CVPR) Computer Vision and Pattern Recognition},
year = {2008},
month = {June},
keywords = {Congealing},
}