by Zoltan Kato
Abstract:
We consider the estimation of diffeomorphic deformations aligning a known binary shape and its distorted observation. The classical solution consists in extracting landmarks, establishing correspondences and then the aligning transformation is obtained via a complex optimization procedure. Herein we present an alternative solution which works without landmark correspondences, is independent of the magnitude of transformation, easy to implement, and has a linear time complexity. The proposed universal framework is capable of recovering linear as well as nonlinear deformations.
Reference:
Zoltan Kato, Linear and nonlinear shape alignment without correspondences, Chapter in Proceedings of International Joint Conference on Computer Vision, Imaging and Computer Graphics - Theory and Applications (Revised Selected Papers) (Paul Richard, Martin Kraus, Robert S. Laramee, Gabriela Csurka, José Braz, eds.), volume 359 of Communications in Computer and Information Science, Rome, Italy, pp. 3-17, 2013, Springer. (Keynote talk)
Bibtex Entry:
@string{springer="Springer"}
@string{ccis="Communications in Computer and Information Science"}
@INCOLLECTION{Kato2013,
author = {Zoltan Kato},
title = {Linear and nonlinear shape alignment without correspondences},
booktitle = {Proceedings of International Joint Conference on Computer Vision,
Imaging and Computer Graphics - Theory and Applications (Revised
Selected Papers)},
publisher = springer,
year = {2013},
editor = {Paul Richard and Martin Kraus and Robert S. Laramee and Gabriela
Csurka and José Braz},
volume = {359},
series = ccis,
pages = {3--17},
address = {Rome, Italy},
note = {Keynote talk},
abstract = {We consider the estimation of diffeomorphic deformations aligning
a known binary shape and its distorted observation. The classical
solution consists in extracting landmarks, establishing correspondences
and then the aligning transformation is obtained via a complex optimization
procedure. Herein we present an alternative solution which works
without landmark correspondences, is independent of the magnitude
of transformation, easy to implement, and has a linear time complexity.
The proposed universal framework is capable of recovering linear
as well as nonlinear deformations.}
}