Abstract: Aiming at the diseases of two types of Solanaceae vegetables, tomato and eggplant, a noise-resistant Solanaceae disease identification network was constructed based on SE-Inception and capsule network, called capsule SE-Inception. The network is mainly divided into two parts: the feature extraction part and the capsule network part. The feature extraction part of the network employed a batch normalization layer (BN) to accelerate the convergence of the network; the SE-Inception structure and multi-scale feature extraction module were used to improve the accuracy of the model. The capsule network part utilized a capsule with a routing iteration number of two and a dimension of sixteen for processing. The experiments were undertaken based on a self-built data set of Solanaceae diseases. Our sample data contains four disease categories: whitefly, powdery mildew, yellow smut, and cotton blight, as well as healthy leaves. Besides, in order to reduce over-fitting, the data was augmented. The experimental results show that the capsule SE-Inception network displays good noise immunity against common Gaussian, salt and pepper, and fuzzy noise; it only needs a limited amount of data to achieve higher recognition accuracy. Based on the same amount of data, the recognition accuracy of capsule SE-Inception network outperforms that of common lightweight models. 

Key words: Solanaceous vegetables, disease recognition, noise immunity, SE-Inception structure, capsule network