Bicycle Chain Shape Models

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt

Standard

Bicycle Chain Shape Models. / Sommer, Stefan Horst; Tatu, Aditya Jayant; Chen, Chen; Jørgensen, Dan; de Bruijne, Marleen; Loog, Marco; Nielsen, Mads; Lauze, Francois Bernard.

Computer Vision and Pattern Recognition Workshops, 2009. CVPR Workshops 2009. IEEE Computer Society Conference on Computer Vision and Pattern Recognition.. IEEE, 2009. s. 157-163.

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt

Harvard

Sommer, SH, Tatu, AJ, Chen, C, Jørgensen, D, de Bruijne, M, Loog, M, Nielsen, M & Lauze, FB 2009, Bicycle Chain Shape Models. i Computer Vision and Pattern Recognition Workshops, 2009. CVPR Workshops 2009. IEEE Computer Society Conference on Computer Vision and Pattern Recognition.. IEEE, s. 157-163, CVPR 2009. IEEE Computer Society Conference on Computer Vision and Pattern Recognition., Miami Beach, USA, 20/06/2009. https://doi.org/10.1109/CVPR.2009.5204053

APA

Sommer, S. H., Tatu, A. J., Chen, C., Jørgensen, D., de Bruijne, M., Loog, M., ... Lauze, F. B. (2009). Bicycle Chain Shape Models. I Computer Vision and Pattern Recognition Workshops, 2009. CVPR Workshops 2009. IEEE Computer Society Conference on Computer Vision and Pattern Recognition. (s. 157-163). IEEE. https://doi.org/10.1109/CVPR.2009.5204053

Vancouver

Sommer SH, Tatu AJ, Chen C, Jørgensen D, de Bruijne M, Loog M o.a. Bicycle Chain Shape Models. I Computer Vision and Pattern Recognition Workshops, 2009. CVPR Workshops 2009. IEEE Computer Society Conference on Computer Vision and Pattern Recognition.. IEEE. 2009. s. 157-163 https://doi.org/10.1109/CVPR.2009.5204053

Author

Sommer, Stefan Horst ; Tatu, Aditya Jayant ; Chen, Chen ; Jørgensen, Dan ; de Bruijne, Marleen ; Loog, Marco ; Nielsen, Mads ; Lauze, Francois Bernard. / Bicycle Chain Shape Models. Computer Vision and Pattern Recognition Workshops, 2009. CVPR Workshops 2009. IEEE Computer Society Conference on Computer Vision and Pattern Recognition.. IEEE, 2009. s. 157-163

Bibtex

@inproceedings{9949efd0656711de8bc9000ea68e967b,
title = "Bicycle Chain Shape Models",
abstract = "In this paper we introduce landmark-based preshapes which allow mixing of anatomical landmarks and pseudo-landmarks, constraining consecutive pseudo-landmarks to satisfy planar equidistance relations. This defines naturally a structure of Riemannian manifold on these preshapes, with a natural action of the group of planar rotations. Orbits define the shapes. We develop a Geodesic Generalized Procrustes Analysis procedure for a sample set on such a preshape spaces and use it to compute Principal Geodesic Analysis. We demonstrate it on an elementary synthetic example as well on a dataset of manually annotated vertebra shapes from X-ray. We re-landmark them consistently and show that PGA captures the variability of the dataset better than its linear counterpart, PCA.",
author = "Sommer, {Stefan Horst} and Tatu, {Aditya Jayant} and Chen Chen and Dan J{\o}rgensen and {de Bruijne}, Marleen and Marco Loog and Mads Nielsen and Lauze, {Francois Bernard}",
year = "2009",
doi = "10.1109/CVPR.2009.5204053",
language = "English",
pages = "157--163",
booktitle = "Computer Vision and Pattern Recognition Workshops, 2009. CVPR Workshops 2009. IEEE Computer Society Conference on Computer Vision and Pattern Recognition.",
publisher = "IEEE",

}

RIS

TY - GEN

T1 - Bicycle Chain Shape Models

AU - Sommer, Stefan Horst

AU - Tatu, Aditya Jayant

AU - Chen, Chen

AU - Jørgensen, Dan

AU - de Bruijne, Marleen

AU - Loog, Marco

AU - Nielsen, Mads

AU - Lauze, Francois Bernard

PY - 2009

Y1 - 2009

N2 - In this paper we introduce landmark-based preshapes which allow mixing of anatomical landmarks and pseudo-landmarks, constraining consecutive pseudo-landmarks to satisfy planar equidistance relations. This defines naturally a structure of Riemannian manifold on these preshapes, with a natural action of the group of planar rotations. Orbits define the shapes. We develop a Geodesic Generalized Procrustes Analysis procedure for a sample set on such a preshape spaces and use it to compute Principal Geodesic Analysis. We demonstrate it on an elementary synthetic example as well on a dataset of manually annotated vertebra shapes from X-ray. We re-landmark them consistently and show that PGA captures the variability of the dataset better than its linear counterpart, PCA.

AB - In this paper we introduce landmark-based preshapes which allow mixing of anatomical landmarks and pseudo-landmarks, constraining consecutive pseudo-landmarks to satisfy planar equidistance relations. This defines naturally a structure of Riemannian manifold on these preshapes, with a natural action of the group of planar rotations. Orbits define the shapes. We develop a Geodesic Generalized Procrustes Analysis procedure for a sample set on such a preshape spaces and use it to compute Principal Geodesic Analysis. We demonstrate it on an elementary synthetic example as well on a dataset of manually annotated vertebra shapes from X-ray. We re-landmark them consistently and show that PGA captures the variability of the dataset better than its linear counterpart, PCA.

U2 - 10.1109/CVPR.2009.5204053

DO - 10.1109/CVPR.2009.5204053

M3 - Article in proceedings

SP - 157

EP - 163

BT - Computer Vision and Pattern Recognition Workshops, 2009. CVPR Workshops 2009. IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

PB - IEEE

ER -

ID: 12872680