Anchored Deformable Face Ensemble Alignment - Robotics Institute Carnegie Mellon University

Anchored Deformable Face Ensemble Alignment

Xin Cheng, Sridha Sridharan, Jason Saraghi, and Simon Lucey
Workshop Paper, ECCV '12 5th Workshop on Non-Rigid Shape Analysis and Deformable Image Alignment (NORDIA '12), pp. 133 - 142, November, 2012

Abstract

At present, many approaches have been proposed for deformable face alignment with varying degrees of success. However, the common drawback to nearly all these approaches is the inaccurate landmark registrations. The registration errors which occur are predominantly heterogeneous (i.e. low error for some frames in a sequence and higher error for others). In this paper we propose an approach for simultaneously aligning an ensemble of deformable face images stemming from the same subject given noisy heterogeneous landmark estimates. We propose that these initial noisy landmark estimates can be used as an “anchor” in conjunction with known state-of-the-art objectives for unsupervised image ensemble alignment. Impressive alignment performance is obtained using well known deformable face fitting algorithms as “anchors”.

BibTeX

@workshop{Cheng-2012-17102,
author = {Xin Cheng and Sridha Sridharan and Jason Saraghi and Simon Lucey},
title = {Anchored Deformable Face Ensemble Alignment},
booktitle = {Proceedings of ECCV '12 5th Workshop on Non-Rigid Shape Analysis and Deformable Image Alignment (NORDIA '12)},
year = {2012},
month = {November},
pages = {133 - 142},
}