Abstract | ||
---|---|---|
Although recognition of objects from 2D projections (i.e. images) has been widely studied among the image processing community, little research has been devoted to recognition using 3D information. A general approach for deriving 3D invariants is proposed in this paper. These invariants can be used as input to a statistical classifier, such as a k-nearest-neighbours algorithm or a neural network. The approach consists of decomposing the object onto an orthonormal basis composed of the eigenvectors of the angular momentum operator from quantum mechanics. Then, using Clebsch-Gordan coefficients, contravariant tensors of order 1 are constructed, and 3D invariants are obtained by tenser contraction. The approach offers an alternative to structural methods for 3D object description and recognition. Experimental results are provided to illustrate the method. |
Year | DOI | Venue |
---|---|---|
1995 | 10.1016/0165-1684(95)00039-G | Signal Processing |
Keywords | Field | DocType |
PATTERN RECOGNITION, ROTATION INVARIANCE, 3D INVARIANCE, TENSOR THEORY, SPHERICAL HARMONICS, ANGULAR MOMENTUM | Mathematical optimization,Scene analysis,Humanities,Geometry,Mathematics | Journal |
Volume | Issue | ISSN |
45 | 1 | 0165-1684 |
Citations | PageRank | References |
33 | 4.30 | 7 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Gilles Burel | 1 | 297 | 113.35 |
Hugues Henocq | 2 | 38 | 6.23 |