Bhandari Mohan, Shahi Tej Bahadur, Neupane Arjun, Walsh Kerry Brian
Department of Science and Technology, Samriddhi College, Bhaktapur 44800, Nepal.
School of Engineering and Technology, Central Queensland University, Norman Gardens, Rockhampton 4701, Australia.
J Imaging. 2023 Feb 20;9(2):53. doi: 10.3390/jimaging9020053.
Early and accurate tomato disease detection using easily available leaf photos is essential for farmers and stakeholders as it help reduce yield loss due to possible disease epidemics. This paper aims to visually identify nine different infectious diseases (bacterial spot, early blight, Septoria leaf spot, late blight, leaf mold, two-spotted spider mite, mosaic virus, target spot, and yellow leaf curl virus) in tomato leaves in addition to healthy leaves. We implemented EfficientNetB5 with a tomato leaf disease (TLD) dataset without any segmentation, and the model achieved an average training accuracy of 99.84% ± 0.10%, average validation accuracy of 98.28% ± 0.20%, and average test accuracy of 99.07% ± 0.38% over 10 cross folds.The use of gradient-weighted class activation mapping (GradCAM) and local interpretable model-agnostic explanations are proposed to provide model interpretability, which is essential to predictive performance, helpful in building trust, and required for integration into agricultural practice.
利用易于获取的叶片照片对番茄病害进行早期准确检测，对农民和利益相关者至关重要，因为这有助于减少可能因病害流行造成的产量损失。本文旨在从视觉上识别番茄叶片中的九种不同传染病（细菌性斑点病、早疫病、叶斑病、晚疫病、叶霉病、二斑叶螨、花叶病毒、靶斑病和黄叶卷曲病毒）以及健康叶片。我们使用番茄叶病（TLD）数据集实现了EfficientNetB5，且未进行任何分割，该模型在10次交叉折叠中平均训练准确率达到99.84%±0.10%，平均验证准确率达到98.28%±0.20%，平均测试准确率达到99.07%±0.38%。我们还提出使用梯度加权类激活映射（GradCAM）和局部可解释模型无关解释来提供模型可解释性，这对预测性能至关重要，有助于建立信任，并且是融入农业实践所必需的。
