| Autor: |
Bingbing Du, Wei Li, Xue Qin |
| Jazyk: |
angličtina |
| Rok vydání: |
2024 |
| Předmět: |
|
| Zdroj: |
Environmental Research Communications, Vol 6, Iss 10, p 105034 (2024) |
| Druh dokumentu: |
article |
| ISSN: |
2515-7620 |
| DOI: |
10.1088/2515-7620/ad87b6 |
| Popis: |
Fruit tree leaf diseases affect both fruit survival rate and orchard revenue. Rapid and accurate classification of tree leaf diseases not only prevents the spread of diseases but also ensures healthy tree growth and improves fruit quality. Existing models mainly focus on individual types of tree leaf diseases, with limited applications in identifying multiple tree leaf diseases. To address the insensitivity of current classification models to disease region features and the issue of increased error rates due to the presence of similar diseases, this study proposes a residual network model combining channel attention mechanism (ECA) and meta-Acon adaptive activation function. The model employs ResNet34 as the backbone network and incorporates the ECA channel attention module after each residual block to focus on relevant feature information. Additionally, a new activation function called meta-Acon is introduced to enhance the model’s generalization ability through its dynamic learning capability. Finally, the model’s recognition performance is improved by fusing bottom-level features with features from other layers using the Feature Pyramid Network (FPN). Experimental results on a dataset augmented with Mosaic processing show that the FPEM-ResNet34 model achieves a classification accuracy of 98.46%. Compared to other common models such as VGG-16, Inception-V1, ResNet50, and Yolo-V8 m, the proposed method in this paper demonstrates more effective improvement in the accuracy of fruit tree leaf classification, making it highly valuable for practical applications. |
| Databáze: |
Directory of Open Access Journals |
| Externí odkaz: |
|
