Name
Abstract | ||
|---|---|---|
This paper presents the results of the evaluation of five deep learning architectures for the classification of soybean pest images. The performance of Inception-v3, Resnet-50, VGG-16, VGG-19 and Xception was evaluated for different fine-tuning and transfer learning strategies over a dataset of 5,000 images captured in real field conditions. The experimental results showed that the deep learning architectures trained with a fine-tuning can lead to higher classification rates in comparison to other approaches, reaching accuracies of up to 93.82%. In addition, deep learning architectures outperformed traditional feature extraction methods, such as SIFT and SURF with Bag-of-Visual Words approach, the semi-supervised learning method OPFSEMImst, and supervised learning methods used to classify images, for example, SVM, k-NN and Random Forest. The results indicate that architectures evaluated can support specialists and farmers in the pest control management in soybean fields. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1016/j.compeg.2020.105836 | COMPUTERS AND ELECTRONICS IN AGRICULTURE |
Keywords | DocType | Volume |
UAV, Remote sensing, Soybean pests, Precision agriculture, Deep learning | Journal | 179 |
ISSN | Citations | PageRank |
0168-1699 | 0 | 0.34 |
References | Authors | |
26 | 7 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Everton Castelão Tetila | 1 | 0 | 1.01 |
| Bruno Brandoli Machado | 2 | 67 | 10.23 |
| Gilberto Astolfi | 3 | 0 | 1.69 |
| Nicolas Alessandro de Souza Belete | 4 | 7 | 2.21 |
| Willian Paraguassu Amorim | 5 | 24 | 4.52 |
| Antonia Railda Roel | 6 | 12 | 1.58 |
| Hemerson Pistori | 7 | 69 | 12.97 |