Please use this identifier to cite or link to this item:
Scopus Web of Science® Altmetric
Type: Conference paper
Title: In defence of RANSAC for outlier rejection in deformable registration
Author: Tran, Q.
Chin, T.J.
Carneiro, G.
Brown, M.
Suter, D.
Citation: Proceedings of the 12th European Conference on Computer Vision, held in Florence, Italy, 7-13 October, 2012 / A. Fitzgibbon, S. Lazebnik, P. Perona, Y. Sato and C. Schmid (eds.): pp.274-287
Publisher: Springer-Verlag
Publisher Place: Germany
Issue Date: 2012
Series/Report no.: Lecture Notes in Computer Science; 7575
ISBN: 9783642337642
ISSN: 0302-9743
Conference Name: European Conference on Computer Vision (12th : 2012 : Florence, Italy)
Statement of
Quoc-Huy Tran, Tat-Jun Chin, Gustavo Carneiro, Michael S. Brown and David Suter
Abstract: This paper concerns the robust estimation of non-rigid deformations from feature correspondences. We advance the surprising view that for many realistic physical deformations, the error of the mismatches (outliers) usually dwarfs the effects of the curvature of the manifold on which the correct matches (inliers) lie, to the extent that one can tightly enclose the manifold within the error bounds of a low-dimensional hyperplane for accurate outlier rejection. This justifies a simple RANSAC-driven deformable registration technique that is at least as accurate as other methods based on the optimisation of fully deformable models. We support our ideas with comprehensive experiments on synthetic and real data typical of the deformations examined in the literature.
Rights: © Springer-Verlag Berlin Heidelberg 2012
RMID: 0020122962
DOI: 10.1007/978-3-642-33765-9_20
Appears in Collections:Computer Science publications

Files in This Item:
File Description SizeFormat 
RA_hdl_77054.pdfRestricted Access5.07 MBAdobe PDFView/Open

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.