by Csaba Domokos, Zoltan Kato
Abstract:
We consider the estimation of 2D affine transformations aligning a known binary shape and its distorted observation. The classical way to solve this registration problem is to find correspondences between the two images and then compute the transformation parameters from these landmarks. In this paper, we propose a novel approach where the exact transformation is obtained as a least-squares solution of a linear system. The basic idea is to fit a Gaussian density to the shapes which preserves the effect of the unknown transformation. It can also be regarded as a consistent coloring of the shapes yielding two rich functions defined over the two shapes to be matched. The advantage of the proposed solution is that it is fast, easy to implement, works without established correspondences and provides a unique and exact solution regardless of the magnitude of transformation.
Reference:
Csaba Domokos, Zoltan Kato, Binary Image Registration Using Covariant Gaussian Densities, In International Conference on Image Analysis and Recognition (A. Campilho, M. Kamel, eds.), volume 5112 of Lecture Notes in Computer Science, Póvoa de Varzim, Portugal, pp. 455-464, 2008, Springer.
Bibtex Entry:
@string{iciar="International Conference on Image Analysis and Recognition"}
@string{lncs="Lecture Notes in Computer Science"}
@string{springer="Springer"}
@InProceedings{Domokos-Kato2008,
author = {Domokos, {Cs}aba and Kato, Zoltan},
title = {Binary Image Registration Using Covariant {G}aussian
Densities},
booktitle = iciar,
year = 2008,
pages = {455--464},
editor = {A. Campilho and M. Kamel},
address = {P\'ovoa de Varzim, Portugal},
month = jun,
volume = 5112,
series = lncs,
publisher = springer,
abstract = {We consider the estimation of 2D affine
transformations aligning a known binary shape and
its distorted observation. The classical way to
solve this registration problem is to find
correspondences between the two images and then
compute the transformation parameters from these
landmarks. In this paper, we propose a novel
approach where the exact transformation is obtained
as a least-squares solution of a linear system. The
basic idea is to fit a Gaussian density to the
shapes which preserves the effect of the unknown
transformation. It can also be regarded as a
consistent coloring of the shapes yielding two rich
functions defined over the two shapes to be
matched. The advantage of the proposed solution is
that it is fast, easy to implement, works without
established correspondences and provides a unique
and exact solution regardless of the magnitude of
transformation.},
pdf = {papers/iciar2008.pdf},
}