CBSNet: An Effective Method for Potato Leaf Disease Classification.

Abstract

As potato is an important crop, potato disease detection and classification are of key significance in guaranteeing food security and enhancing agricultural production efficiency. Aiming at the problems of tiny spots, blurred disease edges, and susceptibility to noise interference during image acquisition and transmission in potato leaf diseases, we propose a CBSNet-based potato disease recognition method. Firstly, a convolution module called Channel Reconstruction Multi-Scale Convolution (CRMC) is designed to extract the upper and lower features by separating the channel features and applying a more optimized convolution to the upper and lower features, followed by a multi-scale convolution operation to capture the key changes more effectively. Secondly, a new attention mechanism, Spatial Triple Attention (STA), is developed, which first reconstructs the spatial dimensions of the input feature maps, then inputs the reconstructed three types of features into each of the three branches and carries out targeted processing according to the importance of the features, thereby improving the model performance. In addition, the Bat-Lion Algorithm (BLA) is introduced, which combines the Lion algorithm and the bat optimization algorithm and makes the optimization process more adaptive by using the bat algorithm to adjust the gradient direction during the updating process of the Lion algorithm. The BLA not only boosts the model's ability to recognize potato disease features but also ensures training stability and enhances the model's robustness in handling noisy images. Experimental results showed that CBSNet achieved an average Accuracy of 92.04% and a Precision of 91.58% on the self-built dataset. It effectively extracts subtle spots and blurry edges of potato leaf diseases, providing strong technical support for disease prevention and control in large-scale potato farming.

Plant phenotyping relevance

ジャガイモ葉の病徴を画像から分類する深層学習手法を開発し、自作データセットで性能評価しており、植物病害状態の取得・推定が中心的である。

Code and data availability

The paper describes a self-built potato leaf disease dataset (derived from PlantVillage) and the CBSNet model, but no supplied block contains any public deposit, availability statement, or authors' URL for the dataset, code, or trained model. PlantVillage/Kaggle sources are cited prior public datasets, not paper-phenot

No evidence-backed public reproduction asset is currently recorded.