A Field Model for Human Detection and Tracking
IEEE Transactions on Pattern Analysis and Machine Intelligence
Dynamic quantization for belief propagation in sparse spaces
Computer Vision and Image Understanding
Shape matching and registration by data-driven EM
Computer Vision and Image Understanding
Discovering Constrained Substructures in Bayesian Trees Using the E.M. Algorithm
ICIAR '08 Proceedings of the 5th international conference on Image Analysis and Recognition
MIAR '08 Proceedings of the 4th international workshop on Medical Imaging and Augmented Reality
Automatic Mutual Nonrigid Registration of Dense Surfaces by Graphical Model Based Inference
SSPR & SPR '08 Proceedings of the 2008 Joint IAPR International Workshop on Structural, Syntactic, and Statistical Pattern Recognition
A robust Graph Transformation Matching for non-rigid registration
Image and Vision Computing
Combinatorial optimization for electrode labeling of EEG caps
MICCAI'07 Proceedings of the 10th international conference on Medical image computing and computer-assisted intervention
Contour matching based on belief propagation
ACCV'06 Proceedings of the 7th Asian conference on Computer Vision - Volume Part II
Finding deformable shapes by point set matching through nonparametric belief propagation
Miar'06 Proceedings of the Third international conference on Medical Imaging and Augmented Reality
Multimedia Tools and Applications
| Hi-index | 0.01 |
A Bayesian network formulation for relational shapematching is presented. The main advantage of the relationalshape matching approach is the obviation ofthe non-rigid spatial mappings used by recent non-rigidmatching approaches. The basic variables that need tobe estimated in the relational shape matching objectivefunction are the global rotation and scale and the localdisplacements and correspondences. The new Bethefree energy approach is used to estimate the pairwisecorrespondences between links of the template graphsand the data. The resulting framework is useful inboth registration and recognition contexts. Results areshown on hand-drawn templates and on 2D transverseT1-weighted MR images.