University of Florida, Institute of Food and Agricultural Sciences (IFAS), North Florida Research and Education Center, Quincy, FL 32351, U.S.A.
Plant Pathology Department, University of Florida, IFAS, Gainesville, FL 32611, U.S.A.
Phytopathology. 2024 Nov;114(11):2431-2441. doi: 10.1094/PHYTO-04-23-0123-R. Epub 2024 Oct 30.
The image-based detection and classification of plant diseases has become increasingly important to the development of precision agriculture. We consider the case of tomato, a high-value crop supporting the livelihoods of many farmers around the world. Many biotic and abiotic plant health issues impede the efficient production of this crop, and laboratory-based diagnostics are inaccessible in many remote regions. Early detection of these plant health issues is essential for efficient and accurate response, prompting exploration of alternatives for field detection. Considering the availability of low-cost smartphones, artificial intelligence-based classification facilitated by mobile phone imagery can be a practical option. This study introduces a smartphone-attachable 30× microscopic lens, used to produce the novel tomato microimaging data set of 8,500 images representing 34 tomato plant conditions on the upper and lower sides of leaves as well as on the surface of tomato fruits. We introduce TOMMicroNet, a 14-layer convolutional neural network (CNN) trained to classify biotic and abiotic plant health issues, and we compare it against six existing pretrained CNN models. We compared two separate pipelines of grouping data for training TOMMicroNet, either presenting all data at once or separating the data into subsets based on the three parts of the plant. Comparing configurations based on cross-validation and F1 scores, we determined that TOMMicroNet attained the highest performance when trained on the complete data set, with 95% classification accuracy on both training and external data sets. Given TOMMicroNet's capabilities when presented with unfamiliar data, this approach has potential for the identification of plant health issues.
基于图像的植物病害检测和分类技术在精准农业的发展中变得越来越重要。我们以番茄为例，番茄是一种高价值作物，为全球许多农民的生计提供了支持。许多生物和非生物的植物健康问题阻碍了这种作物的高效生产，而在许多偏远地区，实验室诊断是无法实现的。早期发现这些植物健康问题对于高效和准确的应对至关重要，这促使人们探索替代方案进行田间检测。考虑到低成本智能手机的可用性，基于人工智能的手机图像分类可以成为一种实用的选择。本研究引入了一个可与智能手机配合使用的 30×显微镜镜头，用于生成 8500 张代表番茄叶片上下表面和番茄果实表面 34 种番茄植物状况的新型番茄显微图像数据集。我们引入了 TOMMicroNet，这是一个 14 层卷积神经网络（CNN），用于对生物和非生物的植物健康问题进行分类，我们将其与六个现有的预训练 CNN 模型进行了比较。我们比较了两种用于训练 TOMMicroNet 的分组数据的独立管道，一种是一次性展示所有数据，另一种是根据植物的三个部分将数据分成子集。通过交叉验证和 F1 分数比较配置，我们确定当在完整数据集上训练时，TOMMicroNet 的性能最高，在训练集和外部数据集上的分类准确率均达到 95%。鉴于 TOMMicroNet 在处理不熟悉数据时的能力，这种方法有可能用于识别植物健康问题。
