Advanced

A ground truth correspondence measure for benchmarking

Karlsson, Johan LU and Ericsson, Anders LU (2006) 18th International Conference on Pattern Recognition, ICPR 2006 3. p.568-573
Abstract
Automatic localisation of correspondences for the construction of Statistical Shape Models from examples has been the focus of intense research during the last decade. Several algorithms are available and benchmarking is needed to rank the different algorithms. Prior work has focused on evaluating the quality of the models produced by the algorithms by measuring compactness, generality and specificity. In this paper problems with these standard measures are discussed. We propose that a ground truth correspondence measure (gcm) is used for benchmarking and in this paper benchmarking is performed on several state of the art algorithms. Minimum Description Length (MDL) with a curvature cost comes out as the winner of the automatic methods.... (More)
Automatic localisation of correspondences for the construction of Statistical Shape Models from examples has been the focus of intense research during the last decade. Several algorithms are available and benchmarking is needed to rank the different algorithms. Prior work has focused on evaluating the quality of the models produced by the algorithms by measuring compactness, generality and specificity. In this paper problems with these standard measures are discussed. We propose that a ground truth correspondence measure (gcm) is used for benchmarking and in this paper benchmarking is performed on several state of the art algorithms. Minimum Description Length (MDL) with a curvature cost comes out as the winner of the automatic methods. Hand marked models turn out to be best but a semi-automatic method is shown to lie in between the best automatic method and the hand built models in performance. (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
Statistical Shape Models, Minimum Description Length (MDL)
host publication
Proceedings - International Conference on Pattern Recognition
volume
3
pages
568 - 573
publisher
IEEE--Institute of Electrical and Electronics Engineers Inc.
conference name
18th International Conference on Pattern Recognition, ICPR 2006
conference location
Hong Kong, China
conference dates
2006-08-20 - 2006-08-24
external identifiers
  • wos:000240705600136
  • scopus:34147101729
ISSN
1051-4651
DOI
10.1109/ICPR.2006.76
language
English
LU publication?
yes
id
8589f93f-d276-45f1-ad8e-1b11750b2efa (old id 616883)
date added to LUP
2007-11-24 11:18:36
date last changed
2019-02-20 08:19:26
@inproceedings{8589f93f-d276-45f1-ad8e-1b11750b2efa,
  abstract     = {Automatic localisation of correspondences for the construction of Statistical Shape Models from examples has been the focus of intense research during the last decade. Several algorithms are available and benchmarking is needed to rank the different algorithms. Prior work has focused on evaluating the quality of the models produced by the algorithms by measuring compactness, generality and specificity. In this paper problems with these standard measures are discussed. We propose that a ground truth correspondence measure (gcm) is used for benchmarking and in this paper benchmarking is performed on several state of the art algorithms. Minimum Description Length (MDL) with a curvature cost comes out as the winner of the automatic methods. Hand marked models turn out to be best but a semi-automatic method is shown to lie in between the best automatic method and the hand built models in performance.},
  author       = {Karlsson, Johan and Ericsson, Anders},
  issn         = {1051-4651},
  keyword      = {Statistical Shape Models,Minimum Description Length (MDL)},
  language     = {eng},
  location     = {Hong Kong, China},
  pages        = {568--573},
  publisher    = {IEEE--Institute of Electrical and Electronics Engineers Inc.},
  title        = {A ground truth correspondence measure for benchmarking},
  url          = {http://dx.doi.org/10.1109/ICPR.2006.76},
  volume       = {3},
  year         = {2006},
}