loading...
 This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Ninth IEEE International Conference on Computer Vision (ICCV'03) - Volume 1
A Bayesian Network Framework for Relational Shape Matching
Nice, France
October 13-October 16
ISBN: 0-7695-1950-4
ASCII Text
x 
 
Anand Rangarajan, James Coughlan, Alan L. Yuille, "A Bayesian Network Framework for Relational Shape Matching," Computer Vision, IEEE International Conference on, vol. 1, pp. 671, Ninth IEEE International Conference on Computer Vision (ICCV'03) - Volume 1, 2003.
 
 
BibTex
x
 
@article{ 10.1109/ICCV.2003.1238412,
author = {Anand Rangarajan and James Coughlan and Alan L. Yuille},
title = {A Bayesian Network Framework for Relational Shape Matching},
journal ={Computer Vision, IEEE International Conference on},
volume = {1},
year = {2003},
isbn = {0-7695-1950-4},
pages = {671},
doi = {http://doi.ieeecomputersociety.org/10.1109/ICCV.2003.1238412},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
}
 
 
RefWorks Procite/RefMan/Endnote
x 
 
TY - CONF
JO - Computer Vision, IEEE International Conference on
TI - A Bayesian Network Framework for Relational Shape Matching
SN - 0-7695-1950-4
SP
EP
A1 - Anand Rangarajan,
A1 - James Coughlan,
A1 - Alan L. Yuille,
PY - 2003
KW - null
VL - 1
JA - Computer Vision, IEEE International Conference on
ER -
 
Anand Rangarajan, University of Florida, Gainesville
James Coughlan, Smith-Kettlewell Institute
A Bayesian network formulation for relational shape matching is presented. The main advantage of the relational shape matching approach is the obviation of the non-rigid spatial mappings used by recent non-rigid matching approaches. The basic variables that need to be estimated in the relational shape matching objective function are the global rotation and scale and the local displacements and correspondences. The new Bethe free energy approach is used to estimate the pairwise correspondences between links of the template graphs and the data. The resulting framework is useful in both registration and recognition contexts. Results are shown on hand-drawn templates and on 2D transverse T1-weighted MR images.
Citation:
Anand Rangarajan, James Coughlan, Alan L. Yuille, "A Bayesian Network Framework for Relational Shape Matching," iccv, vol. 1, pp.671, Ninth IEEE International Conference on Computer Vision (ICCV'03) - Volume 1, 2003
Usage of this product signifies your acceptance of the Terms of Use.