Abstract
Efficient identification of apple leaf diseases (ALDs) can reduce the use of pesticides and increase the quality of apple fruit, which is of significance to smart agriculture. However, existing research into identifying ALDs lacks models/methods that satisfy efficient identification in the wild environment, hindering the application of smart agriculture in the apple industry. Therefore, this paper explores an ACCURATE, LIGHTWEIGHT, and ROBUST convolutional neural network (CNN) called EfficientNet-MG, improving the conventional EfficientNet network by the multistage feature fusion (MSFF) method and gaussian error linear unit (GELU) activation function. The shallow and deep convolutional layers usually contain detailed and semantic information, respectively, but conventional EfficientNets do not fully utilize the different stage convolutional layers. Thus, MSFF was adopted to improve the semantic representation capacity of the last layer of features, and GELU was used to adapt to complicated tasks. Further, a comprehensive ALD dataset called AppleLeaf9 was constructed for the wild environment. The experimental results show that EfficientNet-MG achieves a higher accuracy (99.11%) and fewer parameters (8.42 M) than the five classical CNN models, thus proving that EfficientNet-MG achieves more competitive results on ALD identification.
Funder
National Natural Science Foundation of China
Subject
Agronomy and Crop Science
Reference48 articles.
1. Liu, B., Fan, K., Su, W., and Peng, Y. Two-Stage Convolutional Neural Networks for Diagnosing the Severity of Alternaria Leaf Blotch Disease of the Apple Tree. Remote Sens., 2022. 14.
2. Praba, R.D., Vennila, R., Rohini, G., Mithila, S., and Kavitha, K. Foliar Disease Classification in Apple Trees. Proceedings of the 2021 International Conference on Advancements in Electrical, Electronics, Communication, Computing and Automation (ICAECA).
3. Alvarez-Mendoza, C.I., Teodoro, A., Quintana, J., and Tituana, K. Estimation of Nitrogen in the Soil of Balsa Trees in Ecuador Using Unmanned Aerial Vehicles. Proceedings of the IGARSS 2020—2020 IEEE International Geoscience and Remote Sensing Symposium.
4. AI-powered banana diseases and pest detection;Selvaraj;Plant Methods,2019
5. Spectral analysis of winter wheat leaves for detection and differentiation of diseases and insects;Yuan;Field Crop Res.,2014
Cited by
16 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献