A Scale-Space Approach to Landmark Constrained Image Registration

Eldad Haber; Stefan Heldmann; Jan Modersitzki

doi:10.1007/978-3-642-02256-2_51

A Scale-Space Approach to Landmark Constrained Image Registration

Eldad Haber, Stefan Heldmann, Jan Modersitzki

Abstract

Adding external knowledge improves the results for ill-posed problems. In this paper we present a new multi-level optimization framework for image registration when adding landmark constraints on the transformation. Previous approaches are based on a fixed discretization and lack of allowing for continuous landmark positions that are not on grid points. Our novel approach overcomes these problems such that we can apply multi-level methods which have been proven being crucial to avoid local minima in the course of optimization. Furthermore, for our numerical method we are able to use constraint elimination such that we trace back the landmark constrained problem to a unconstrained optimization leading to an efficient algorithm.

Original language	English
Title of host publication	Scale Space and Variational Methods in Computer Vision
Editors	Xue-Cheng Tai, Knut Mørken, Marius Lysaker, Knut-Andreas Lie
Number of pages	12
Volume	5567 LNCS
Place of Publication	Berlin, Heidelberg
Publisher	Springer Berlin Heidelberg
Publication date	01.06.2009
Pages	612-623
ISBN (Print)	978-3-642-02255-5
ISBN (Electronic)	978-3-642-02256-2
DOIs	https://doi.org/10.1007/978-3-642-02256-2_51
Publication status	Published - 01.06.2009
Event	2nd International Conference on Scale Space and Variational Methods in Computer Vision - Voss, Norway Duration: 01.06.2009 → 05.06.2009 Conference number: 77044

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1007/978-3-642-02256-2_51

Cite this

Haber, E., Heldmann, S., & Modersitzki, J. (2009). A Scale-Space Approach to Landmark Constrained Image Registration. In X.-C. Tai, K. Mørken, M. Lysaker, & K.-A. Lie (Eds.), Scale Space and Variational Methods in Computer Vision (Vol. 5567 LNCS, pp. 612-623). (Lecture Notes in Computer Science ; Vol. 5567 LNCS). Springer Berlin Heidelberg. https://doi.org/10.1007/978-3-642-02256-2_51

Haber, Eldad ; Heldmann, Stefan ; Modersitzki, Jan. / A Scale-Space Approach to Landmark Constrained Image Registration. Scale Space and Variational Methods in Computer Vision. editor / Xue-Cheng Tai ; Knut Mørken ; Marius Lysaker ; Knut-Andreas Lie. Vol. 5567 LNCS Berlin, Heidelberg : Springer Berlin Heidelberg, 2009. pp. 612-623 (Lecture Notes in Computer Science ).

@inproceedings{571713726bbc456397580089be3260d1,

title = "A Scale-Space Approach to Landmark Constrained Image Registration",

abstract = "Adding external knowledge improves the results for ill-posed problems. In this paper we present a new multi-level optimization framework for image registration when adding landmark constraints on the transformation. Previous approaches are based on a fixed discretization and lack of allowing for continuous landmark positions that are not on grid points. Our novel approach overcomes these problems such that we can apply multi-level methods which have been proven being crucial to avoid local minima in the course of optimization. Furthermore, for our numerical method we are able to use constraint elimination such that we trace back the landmark constrained problem to a unconstrained optimization leading to an efficient algorithm.",

author = "Eldad Haber and Stefan Heldmann and Jan Modersitzki",

year = "2009",

month = jun,

day = "1",

doi = "10.1007/978-3-642-02256-2_51",

language = "English",

isbn = "978-3-642-02255-5",

volume = "5567 LNCS",

series = "Lecture Notes in Computer Science ",

publisher = "Springer Berlin Heidelberg",

pages = "612--623",

editor = "Xue-Cheng Tai and Knut M{\o}rken and Marius Lysaker and Knut-Andreas Lie",

booktitle = "Scale Space and Variational Methods in Computer Vision",

note = "2nd International Conference on Scale Space and Variational Methods in Computer Vision, SSVM 2009 ; Conference date: 01-06-2009 Through 05-06-2009",

}

Haber, E, Heldmann, S & Modersitzki, J 2009, A Scale-Space Approach to Landmark Constrained Image Registration. in X-C Tai, K Mørken, M Lysaker & K-A Lie (eds), Scale Space and Variational Methods in Computer Vision. vol. 5567 LNCS, Lecture Notes in Computer Science , vol. 5567 LNCS, Springer Berlin Heidelberg, Berlin, Heidelberg, pp. 612-623, 2nd International Conference on Scale Space and Variational Methods in Computer Vision, Voss, Norway, 01.06.09. https://doi.org/10.1007/978-3-642-02256-2_51

A Scale-Space Approach to Landmark Constrained Image Registration. / Haber, Eldad; Heldmann, Stefan ; Modersitzki, Jan.
Scale Space and Variational Methods in Computer Vision. ed. / Xue-Cheng Tai; Knut Mørken; Marius Lysaker; Knut-Andreas Lie. Vol. 5567 LNCS Berlin, Heidelberg: Springer Berlin Heidelberg, 2009. p. 612-623 (Lecture Notes in Computer Science ; Vol. 5567 LNCS).

Research output: Chapters in Books/Reports/Conference Proceedings › Conference contribution › peer-review

TY - GEN

T1 - A Scale-Space Approach to Landmark Constrained Image Registration

AU - Haber, Eldad

AU - Heldmann, Stefan

AU - Modersitzki, Jan

N1 - Conference code: 77044

PY - 2009/6/1

Y1 - 2009/6/1

N2 - Adding external knowledge improves the results for ill-posed problems. In this paper we present a new multi-level optimization framework for image registration when adding landmark constraints on the transformation. Previous approaches are based on a fixed discretization and lack of allowing for continuous landmark positions that are not on grid points. Our novel approach overcomes these problems such that we can apply multi-level methods which have been proven being crucial to avoid local minima in the course of optimization. Furthermore, for our numerical method we are able to use constraint elimination such that we trace back the landmark constrained problem to a unconstrained optimization leading to an efficient algorithm.

AB - Adding external knowledge improves the results for ill-posed problems. In this paper we present a new multi-level optimization framework for image registration when adding landmark constraints on the transformation. Previous approaches are based on a fixed discretization and lack of allowing for continuous landmark positions that are not on grid points. Our novel approach overcomes these problems such that we can apply multi-level methods which have been proven being crucial to avoid local minima in the course of optimization. Furthermore, for our numerical method we are able to use constraint elimination such that we trace back the landmark constrained problem to a unconstrained optimization leading to an efficient algorithm.

UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-69049102396&origin=inward&txGid=7dad6aa8d1bb830eb22c71843d76fe9e

U2 - 10.1007/978-3-642-02256-2_51

DO - 10.1007/978-3-642-02256-2_51

M3 - Conference contribution

SN - 978-3-642-02255-5

VL - 5567 LNCS

T3 - Lecture Notes in Computer Science

SP - 612

EP - 623

BT - Scale Space and Variational Methods in Computer Vision

A2 - Tai, Xue-Cheng

A2 - Mørken, Knut

A2 - Lysaker, Marius

A2 - Lie, Knut-Andreas

PB - Springer Berlin Heidelberg

CY - Berlin, Heidelberg

T2 - 2nd International Conference on Scale Space and Variational Methods in Computer Vision

Y2 - 1 June 2009 through 5 June 2009

ER -

A Scale-Space Approach to Landmark Constrained Image Registration

Abstract

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this