Classification of aircraft images using different architectures of radial basis function neural network : a performance comparison
Four Radial Basis Network architectures are evaluated for their performance in terms of classification accuracy and computation time. The architectures are Radial Basis Neural Network, Goal Oriented Radial Basis Architecture, Generalized Gaussian Network, Probabilistic Neural Network. Zemike Invaria...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Penerbit UTM Press,
2008-12.
|
| Subjects: | |
| Online Access: | Get fulltext |
| Summary: | Four Radial Basis Network architectures are evaluated for their performance in terms of classification accuracy and computation time. The architectures are Radial Basis Neural Network, Goal Oriented Radial Basis Architecture, Generalized Gaussian Network, Probabilistic Neural Network. Zemike Invariant Moment is utilized to extract a set of features from the aircraft image. Each of the architectures is used to'classify the image feature vectors. It is found that Generalized Gaussian Neural Network Architecture portrays perfect classification of 100% at a fastest time. Hence, the Generalized Gaussian Neural Network Architecture has a high potential to be adopted to classify images in a real-time environment. |
|---|