Strawberry Disease and Pest Identification and Control Based on SE-ResNeXt50 Model

Abstract

Strawberry disease and pest identification and control were rarely studied, with few high-quality open image datasets to date. In view of this situation, firstly, the images of common strawberry pests and diseases of 13 categories were collected both online and offline independently to be constructed into datasets. Secondly, the SE-ResNeXt50 model was created, which had better usability than the residual network model ResNet50. To be specific, the Inception was combined with the ResNet50 model to widen the network, 32 branches were set, and the attention mechanism, the squeeze and excitation module (SE), was also imported, which solved the problems of the complex image background and information interference and improved the identification efficiency and accuracy of the model. The results showed that the accuracy of the SE-ResNeXt50 model, reaching 89.3%, was 8% higher than that of the ResNet50 model. The SEResNeXt50 model had plateaued after iterating 15 times, indicating its good identification performance. Besides, the SEResNeXt50 model, which was developed based on the data obtained in real life, had good generalization ability and robustness, better meeting the demands of strawberry growers. A WeChat mini-program for strawberry disease and pest identification based on the SE-ResNeXt50 model was developed, enabling the fruit growers to identify the strawberry pests and diseases easily and get prevention suggestions, promoting the development of the strawberry industry.