A general scheme for training and optimization of the Grenander deformable template model

Rune Fisker; Nette Schultz; N. Duta; Jens Michael Carstensen

doi:10.1109/CVPR.2000.855888

A general scheme for training and optimization of the Grenander deformable template model

Rune Fisker
, Nette Schultz
, N. Duta
, Jens Michael Carstensen

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

315 Downloads (Orbit)

Abstract

General deformable models have reduced the need for hand crafting new models for every new problem, but still most of the general models rely on manual interaction by an expert, when applied to a new problem, e.g. for selecting parameters and initialization. We propose a full and unified scheme for applying the general deformable template model proposed by (Grenander et al., 1991) to a new problem with minimal manual interaction, beside supplying a training set, which can be done by a non-expert user. The main contributions compared to previous work are a supervised learning scheme for the model parameters, a very fast general initialization algorithm and an adaptive likelihood model based on local means. The model parameters are trained by a combination of a 2D shape learning algorithm and a maximum likelihood based criteria. The fast initialization algorithm is based on a search approach using a filter interpretation of the likelihood model.

Original language	English
Title of host publication	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume	1
Publisher	IEEE
Publication date	2000
Pages	698-705
ISBN (Print)	0-7695-0662-3
DOIs	https://doi.org/10.1109/CVPR.2000.855888
Publication status	Published - 2000
Event	2000 IEEE Conference on Computer Vision and Pattern Recognition - Hilton Head, United States Duration: 13 Jun 2000 → 15 Jun 2000 https://ieeexplore.ieee.org/xpl/conhome/6894/proceeding

Conference

Conference	2000 IEEE Conference on Computer Vision and Pattern Recognition
Country/Territory	United States
City	Hilton Head
Period	13/06/2000 → 15/06/2000
Internet address	https://ieeexplore.ieee.org/xpl/conhome/6894/proceeding

Bibliographical note

Copyright 2000 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

Access to Document

10.1109/CVPR.2000.855888

FiskerFinal published version, 372 KB

OpenUrl availability

Check availability in DTU Findit

Cite this

@inproceedings{4fa9fd5312da4d1088dd7dde33054259,

title = "A general scheme for training and optimization of the Grenander deformable template model",

abstract = "General deformable models have reduced the need for hand crafting new models for every new problem, but still most of the general models rely on manual interaction by an expert, when applied to a new problem, e.g. for selecting parameters and initialization. We propose a full and unified scheme for applying the general deformable template model proposed by (Grenander et al., 1991) to a new problem with minimal manual interaction, beside supplying a training set, which can be done by a non-expert user. The main contributions compared to previous work are a supervised learning scheme for the model parameters, a very fast general initialization algorithm and an adaptive likelihood model based on local means. The model parameters are trained by a combination of a 2D shape learning algorithm and a maximum likelihood based criteria. The fast initialization algorithm is based on a search approach using a filter interpretation of the likelihood model.",

author = "Rune Fisker and Nette Schultz and N. Duta and Carstensen, \{Jens Michael\}",

note = "Copyright 2000 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.; 2000 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2000 ; Conference date: 13-06-2000 Through 15-06-2000",

year = "2000",

doi = "10.1109/CVPR.2000.855888",

language = "English",

isbn = "0-7695-0662-3",

volume = "1",

pages = "698--705",

booktitle = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

publisher = "IEEE",

address = "United States",

url = "https://ieeexplore.ieee.org/xpl/conhome/6894/proceeding",

}

Fisker, R, Schultz, N, Duta, N & Carstensen, JM 2000, A general scheme for training and optimization of the Grenander deformable template model. in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. vol. 1, IEEE, pp. 698-705, 2000 IEEE Conference on Computer Vision and Pattern Recognition, Hilton Head, South Carolina, United States, 13/06/2000. https://doi.org/10.1109/CVPR.2000.855888

A general scheme for training and optimization of the Grenander deformable template model. / Fisker, Rune; Schultz, Nette; Duta, N. et al.
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Vol. 1 IEEE, 2000. p. 698-705.

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

TY - GEN

T1 - A general scheme for training and optimization of the Grenander deformable template model

AU - Fisker, Rune

AU - Schultz, Nette

AU - Duta, N.

AU - Carstensen, Jens Michael

N1 - Copyright 2000 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

PY - 2000

Y1 - 2000

N2 - General deformable models have reduced the need for hand crafting new models for every new problem, but still most of the general models rely on manual interaction by an expert, when applied to a new problem, e.g. for selecting parameters and initialization. We propose a full and unified scheme for applying the general deformable template model proposed by (Grenander et al., 1991) to a new problem with minimal manual interaction, beside supplying a training set, which can be done by a non-expert user. The main contributions compared to previous work are a supervised learning scheme for the model parameters, a very fast general initialization algorithm and an adaptive likelihood model based on local means. The model parameters are trained by a combination of a 2D shape learning algorithm and a maximum likelihood based criteria. The fast initialization algorithm is based on a search approach using a filter interpretation of the likelihood model.

AB - General deformable models have reduced the need for hand crafting new models for every new problem, but still most of the general models rely on manual interaction by an expert, when applied to a new problem, e.g. for selecting parameters and initialization. We propose a full and unified scheme for applying the general deformable template model proposed by (Grenander et al., 1991) to a new problem with minimal manual interaction, beside supplying a training set, which can be done by a non-expert user. The main contributions compared to previous work are a supervised learning scheme for the model parameters, a very fast general initialization algorithm and an adaptive likelihood model based on local means. The model parameters are trained by a combination of a 2D shape learning algorithm and a maximum likelihood based criteria. The fast initialization algorithm is based on a search approach using a filter interpretation of the likelihood model.

U2 - 10.1109/CVPR.2000.855888

DO - 10.1109/CVPR.2000.855888

M3 - Article in proceedings

SN - 0-7695-0662-3

VL - 1

SP - 698

EP - 705

BT - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

PB - IEEE

T2 - 2000 IEEE Conference on Computer Vision and Pattern Recognition

Y2 - 13 June 2000 through 15 June 2000

ER -

A general scheme for training and optimization of the Grenander deformable template model

Abstract

Conference

Bibliographical note

Access to Document

OpenUrl availability

Fingerprint

Cite this