Research Article
Macroscopic Rock Texture Image Classification Using a Hierarchical Neuro-Fuzzy Class Method
Table 3
Neural network Configurations used to classify the following rock subclasses: gneiss, basalt, diabase, and rhyolite.
| Rock | Database test | Number of layers | Number of neurons in input layer | Number of neurons in first hidden layer | Number of neurons in second hidden layer | Number of neurons in output layer |
| Gneiss | Gneiss1 |
3 | 3 | 5 |
â |
2 | Gneiss2 | 9 | 9 | Gneiss3 | 12 | 9 | Gneiss4 | 11 | 9 |
| Basalt | Basalt1 |
4 | 3 | 10 |
10 |
4 | Basalt2 | 9 | 10 | Basalt3 | 12 | 10 | Basalt4 | 11 | 10 |
| Diabase | Diabase1 |
4 | 3 | 20 | 15 |
5 | Diabase2 | 9 | 20 | 15 | Diabase3 | 12 | 20 | 25 | Diabase4 | 11 | 20 | 15 |
| Rhyolite | Rhyolite1 |
4 | 3 | 20 |
15 |
5 | Rhyolite2 | 9 | 20 | Rhyolite3 | 12 | 20 | Rhyolite4 | 11 | 20 |
|
|