Construction of deep learning-based disease detection model in plants.

Abstract

Accurately detecting disease occurrences of crops in early stage is essential for quality and yield of crops through the decision of an appropriate treatments. However, detection of disease needs specialized knowledge and long-term experiences in plant pathology. Thus, an automated system for disease detecting in crops will play an important role in agriculture by constructing early detection system of disease. To develop this system, construction of a stepwise disease detection model using images of diseased-healthy plant pairs and a CNN algorithm consisting of five pre-trained models. The disease detection model consists of three step classification models, crop classification, disease detection, and disease classification. The 'unknown' is added into categories to generalize the model for wide application. In the validation test, the disease detection model classified crops and disease types with high accuracy (97.09%). The low accuracy of non-model crops was improved by adding these crops to the training dataset implicating expendability of the model. Our model has the potential to apply to smart farming of Solanaceae crops and will be widely used by adding more various crops as training dataset.

Plant phenotyping relevance

植物画像から病害の有無・種類を推定するCNNモデルの構築と検証が研究の中心であり、植物病害状態を直接評価する画像ベース表現型計測に該当する。

Code and data availability

The paper's plant disease detection models were trained on leaf image datasets explicitly released publicly: the PlantVillage dataset (GitHub) and the AI-hub strawberry field image dataset. Both are cited in the Data availability statement with exact URLs. No author analysis code or trained model checkpoints are stated