Title | ||
---|---|---|
Fusarium Damaged Kernels Detection Using Transfer Learning on Deep Neural Network Architecture. |
Abstract | ||
---|---|---|
The present work shows the application of transfer learning for a pre-trained deep neural network (DNN), using a small image dataset ($approx$ 12,000) on a single workstation with enabled NVIDIA GPU card that takes up to 1 hour to complete the training task and archive an overall average accuracy of $94.7%$. The DNN presents a $20%$ score of misclassification for an external test dataset. The accuracy of the proposed methodology is equivalent to ones using HSI methodology $(81%-91%)$ used for the same task, but with the advantage of being independent on special equipment to classify wheat kernel for FHB symptoms. |
Year | Venue | Field |
---|---|---|
2018 | arXiv: Learning | Kernel (linear algebra),Transfer of learning,Neural network architecture,Workstation,Artificial intelligence,Artificial neural network,Machine learning,Mathematics |
DocType | Volume | Citations |
Journal | abs/1802.00030 | 0 |
PageRank | References | Authors |
0.34 | 2 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Márcio Nicolau | 1 | 0 | 0.34 |
Márcia Barrocas Moreira Pimentel | 2 | 0 | 0.34 |
Casiane Salete Tibola | 3 | 0 | 0.34 |
José Maurício Cunha Fernandes | 4 | 0 | 1.01 |
Willingthon Pavan | 5 | 1 | 2.41 |