Abstract | ||
---|---|---|
Recently Poggio and Edelman have shown that for each object there exists a smooth mapping from an arbitrary view to its standard view and that the mapping can be learned from a sparse data set. In this paper, we extend their scheme further to deal with 3D flexible objects. We show the mappings from an arbitrary view to the standard view, and its rotated view can be synthesized even for a flexible object by learning from examples. To classify 3D flexible objects, we propose two methods, which do not require any special knowledge on the target flexible objects. They are: (1) learning the characteristic function of the object and (2) learning the view-change transformation. We show their performance by computer simulations. |
Year | DOI | Venue |
---|---|---|
1994 | 10.1007/BF00200335 | Biological Cybernetics |
Keywords | Field | DocType |
Computer Simulation,Characteristic Function,Smooth Mapping,Special Knowledge,Sparse Data | Existential quantification,Characteristic function (probability theory),Artificial intelligence,Artificial neural network,Cognition,Perception,Sparse matrix,Mathematics,Mental representation | Journal |
Volume | Issue | ISSN |
70 | 4 | 0340-1200 |
Citations | PageRank | References |
0 | 0.34 | 5 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Minoru Maruyama | 1 | 98 | 13.89 |
Teruhiko Teraoka | 2 | 95 | 5.44 |
Shigeru Abe | 3 | 13 | 3.85 |