Enhanced residual-attention deep neural network for disease classification in maize leaf images

Abstract

Disease classification in maize plant is necessary for immediate treatment to enhance agricultural production and assure global food sustainability. Recent advancements in deep learning, specifically convolutional neural networks, have shown outstanding potential for image classification. This study presents Maize Net, a convolutional neural network model that precisely identifies diseases in maize leaves. Maize Net uses an attention mechanism to increase the model's efficiency by focusing on the relevant features and residual learning to improve the gradient flow. This also addresses the vanishing gradient problem while training deeper neural networks. A five-fold cross-validation test is conducted for generalization across the dataset, generating five models based on distinct training and testing sets. The macro-average of all evaluation metrics is considered to address the dataset's class imbalance problem. Maize Net achieved an average F1-score of 0.9509, recall of 0.9497, precision of 0.9525, and classification accuracy of 0.9595. These outcomes demonstrate MaizeNet's robustness and reliability in automated plant disease classification.

Plant phenotyping relevance

トウモロコシ葉画像から病害状態を推定する深層学習モデルを開発し、交差検証で性能を評価しており、植物フェノタイピング手法が中心である。

Code and data availability

The paper's maize leaf image dataset is stated to be publicly available on Kaggle (the Ghose et al. corn-or-maize-leaf-disease-dataset), which is a paper-specific, public phenotype image asset. However, the only availability statement is the Kaggle URL in the Data availability section, which does not match any entry in

No evidence-backed public reproduction asset is currently recorded.