Research Article
Intelligent Image Recognition System for Marine Fouling Using Softmax Transfer Learning and Deep Convolutional Neural Networks
Table 7
CNN models test results.
| Data | Model name | Epochs | Batch size | Acorn barnacles | Gooseneck barnacle | Algae | Tunicate | Zebra mussel | Accuracy |
| Dataset 1 | CNN_Model.h1 | 100 | 96 | 6/10 | 10/10 | 10/10 | 9/10 | 9/10 | 89% | CNN_Model.h2 | 75 | 8/10 | 10/10 | 9/10 | 9/10 | 6/10 | 87% | CNN_Model.h3 | 50 | 10/10 | 6/10 | 8/10 | 7/10 | 6/10 | 69% | CNN_Model.h4 | 25 | 8/10 | 7/10 | 8/10 | 9/10 | 1/10 | 67% |
| Dataset 2 | CNN_Model.h5 | 100 | 96 | 4/10 | 8/10 | 7/10 | 10/10 | 4/10 | 72% | CNN_Model.h6 | 75 | 8/10 | 6/10 | 8/10 | 10/10 | 3/10 | 69% | CNN_Model.h7 | 50 | 9/10 | 6/10 | 8/10 | 9/10 | 6/10 | 78% | CNN_Model.h8 | 25 | 9/10 | 2/10 | 9/10 | 9/10 | 3/10 | 67% |
|
|