Authors

Abstract

Crop diseases have an important impact on the safe production of food. Therefore, the automated identification of pre-crop diseases is very important for farmers to increase production and income. In this paper, a tomato leaf disease identification method based on the optimized MobileNetV2 model is proposed. A dataset of 20,400 tomato disease images was created based on tomato disease images taken from the greenhouse and obtained from the PlantVillage database. The optimized MobileNetV2 model was trained with the dataset to obtain a classification model for tomato leaf diseases. The average recognition accuracy of the model is 98.3% and the recall rate is 94.9%, which is 1.2% and 3.9% higher than the original model, respectively, after experimental validation. The average prediction speed of the model for a single image is about 76 ms, which is 2.94% better than the original model. To verify the performance of the optimized MobileNetV2 model, it was compared with the Xception, Inception, and VGG16 feature extraction network models using migration learning, respectively. The experimental results show that the average recognition accuracy of the model is 0.4 to 2.4 percentage points higher than that of the Xception, Inception, and VGG16 models. It can provide technical support for the identification of tomato diseases, and is also important for plant growth monitoring under precision agriculture.

Abstract in Chinese

农作物病害威胁粮食的安全生产。因此，农作物前期病害的自动化识别对农民增产增收十分重要。本文提出了一种基于优化的MobileNetV2模型的番茄叶部病害识别方法。基于从温室拍摄及PlantVillage数据库获取的番茄病害图像，创建了一个包含20400张番茄病害图像数据集。用数据集对优化的MobileNetV2模型进行训练，获得了番茄叶部病害的分类模型。经试验验证，该模型的平均识别准确率为98.3%，召回率为94.9%，比原模型分别提高了1.2%和3.9%。该模型对单张图片的平均预测速度约为76ms，比原模型提高了2.94%。为验证优化的MobileNetV2模型的性能，分别与使用迁移学习的Xception、Inception、VGG16特征提取网络模型进行了比较。试验结果表明，该模型的平均识别准确率比Xception、Inception、VGG16模型高出了0.4～2.4个百分点。可为番茄病害的识别提供技术支持，同时对精准农业下的植物生长监控具有重要意义。