Abstract
Accurate identification of soybean leaf diseases is essential to improving quality and yield. Aiming at the problem of insufficient data volume that may lead to model overfitting and low recognition ability, this paper proposes a hypergraph cell membrane computing network model for soybean disease identification (HcmcNet). The main components of HcmcNet are the pyramid convolutional feature extraction membrane, the ordinary feature extraction membrane, the U-type feature extraction membrane, and the dynamic attention membrane. The three parallel feature extraction membranes are designed to improve the model's ability to capture disease features. The dynamic attention membrane aims to enhance the model's expressiveness and performance by dynamically adjusting the attentional weights of the three feature extraction membranes to fuse the disease features effectively. Soybean leaf disease images were used to create the dataset and conduct experiments. The experimental results show that HcmcNet achieves 98% accuracy on the test set. Compared with classical models, HcmcNet shows obvious advantages in several evaluation metrics. We also conducted experiments on public datasets. The results show that it is feasible to use HcmcNet for soybean leaf disease recognition, and HcmcNet has higher classification accuracy and stronger generalization ability on small sample datasets. HcmcNet has great application prospects in soybean leaf disease recognition.