Name
Abstract | ||
|---|---|---|
A new method for automatically building statistical shape models from a set of training ex amples and in particular from a class of hands. I n this method, landmark ex traction is achiev ed using a self- organising neural network , the Growing Neural Gas ( GNG) , which is used to preserv e the topology of any input space. Using GNG, the topological relations of a giv en set of deformable shapes can be learned. We describe how shape models can be built automatically by posing the correspondence problem on the behav iour of self- organising network s that are capable of adapting their topology to an input manifold, and due to their dynamic character to readapt it to the shape of the obj ects. Results are giv en for the training set of hand outlines, showing that the proposed method preserv es accurate models. |
Year | Venue | Keywords |
|---|---|---|
2005 | MVA | neural network,correspondence problem |
Field | DocType | Citations |
Training set,Computer vision,Pattern recognition,Artificial intelligence,Landmark,Correspondence problem,Artificial neural network,Mathematics,Neural gas,Manifold | Conference | 0 |
PageRank | References | Authors |
0.34 | 7 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Anastassia Angelopoulou | 1 | 102 | 21.29 |
| José García Rodríguez | 2 | 0 | 0.34 |
| Alexandra Psarrou | 3 | 199 | 27.14 |