Abstract | ||
---|---|---|
This paper is concerned with the types of invariance exhibited by Radial Basis Function (RBF) neural networks when used for human face classification, and the generalisation abilities arising from this behaviour. Experiments using face images in ranges from face-on to profile show the RBF network's invariance to 2-D shift, scale and y-axis rotation. Finally, the suitability of RBF techniques for future, more automated face classification purposes is discussed. |
Year | DOI | Venue |
---|---|---|
1995 | 10.1007/BF02311576 | Neural Processing Letters |
Keywords | Field | DocType |
Neural Network,Artificial Intelligence,Basis Function,Complex System,Nonlinear Dynamics | Radial basis function network,Radial basis function,Invariant (physics),Pattern recognition,Generalization,Computer science,Hierarchical RBF,Artificial intelligence,Basis function,Artificial neural network,Machine learning | Journal |
Volume | Issue | ISSN |
2 | 3 | 1370-4621 |
Citations | PageRank | References |
14 | 2.21 | 5 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
jon howell | 1 | 585 | 39.63 |
Hilary Buxton | 2 | 491 | 135.93 |