Detection of gray mold disease and its severity on strawberry using deep learning networks

Abstract

Gray mold caused by necrotrophic fungus pathogen (Botrytis cinerea) is a lethal disease, which affects various plants. It is also a common disease in strawberry, limiting the yield. Therefore, the detection and quantification of gray mold disease in the field is indispensable. Most of the deep convolutional neural networks (CNNs) were used for the plant disease identification and classification based on the highest probability value scored by the network. However, pixel-level segmentation allows quantifying the disease severity in the plant, which is crucial to determine the pesticides' dose. Disease severity is also a useful parameter for monitoring the plant's resistance against a particular disease. Therefore, accurate quantification of plant disease is of utmost necessity in agriculture. In this circumstance, a deep learning-based semantic segmentation model was designed and tested to detect and measure the strawberry plants' gray mold disease. For this purpose, three concentrations of 1 x 10(3), 1 x 10(5), 1 x 10(7) CFU/mL pathogen were inoculated on each group of 10 strawberry plants, and consequent occurrence of disease and its intensity over time were observed. The model performance was evaluated using pixel accuracy, dice accuracy, and intersection over union (IoU) metrics using fivefold cross-validation method. The results were compared with the results obtained from the XGBoost model, K-means, and Otsu image processing algorithms. The pixel, dice, and IoU accuracies were achieved the highest from the Unet model followed by the XGBoost model on 80 test images. Results showed that the Unet model surpasses the conventional XGBoost, K-means, and image processing technique in detecting and quantifying gray mold disease. Thus, a deep learning Unet can be a nifty tool assisting the farmers and agronomists in disease severity measurement.