College of Biological and Agricultural Engineering, Jilin University, Changchun, Jilin, China.
PLoS One. 2021 Sep 3;16(9):e0257008. doi: 10.1371/journal.pone.0257008. eCollection 2021.
In this study, the feasibility of classifying soybean frogeye leaf spot (FLS) is investigated. Leaf images and hyperspectral reflectance data of healthy and FLS diseased soybean leaves were acquired. First, image processing was used to classify FLS to create a reference for subsequent analysis of hyperspectral data. Then, dimensionality reduction methods of hyperspectral data were used to obtain the relevant information pertaining to FLS. Three single methods, namely spectral index (SI), principal component analysis (PCA), and competitive adaptive reweighted sampling (CARS), along with a PCA and SI combined method, were included. PCA was used to select the effective principal components (PCs), and evaluate SIs. Characteristic wavelengths (CWs) were selected using CARS. Finally, the full wavelengths, CWs, effective PCs, SIs, and significant SIs were divided into 14 datasets (DS1-DS14) and used as inputs to build the classification models. Models' performances were evaluated based on the classification accuracy for both the overall and individual classes. Our results suggest that the FLS comprised of five classes based on the proportion of total leaf surface covered with FLS. In the PCA and SI combination model, 5 PCs and 20 SIs with higher weight coefficient of each PC were extracted. For hyperspectral data, 20 CWs and 26 effective PCs were also selected. Out of the 14 datasets, the model input variables provided by five datasets (DS2, DS3, DS4, DS10, and DS11) were more superior than those of full wavelengths (DS1) both in support vector machine (SVM) and least squares support vector machine (LS-SVM) classifiers. The models developed using these five datasets achieved overall accuracies ranging from 91.8% to 94.5% in SVM, and 94.5% to 97.3% in LS-SVM. In addition, they improved the classification accuracies by 0.9% to 3.6% (SVM) and 0.9% to 3.7% (LS-SVM).
本研究旨在探讨大豆蛙眼病（FLS）分类的可行性。采集了健康和患有 FLS 大豆叶片的图像和高光谱反射率数据。首先，使用图像处理技术对 FLS 进行分类，为后续分析高光谱数据创建参考。然后，使用高光谱数据的降维方法获取与 FLS 相关的信息。本研究纳入了三种单一方法，即光谱指数（SI）、主成分分析（PCA）和竞争自适应重加权采样（CARS），以及 PCA 和 SI 结合方法。PCA 用于选择有效的主成分（PCs），并评估 SI。CARS 用于选择特征波长（CWs）。最后，将全波长、CWs、有效 PCs、SI 和显著 SI 分为 14 个数据集（DS1-DS14），并将其作为输入构建分类模型。基于整体和个别类别的分类准确率评估模型性能。我们的研究结果表明，基于叶片表面被 FLS 覆盖的总面积，FLS 可分为五类。在 PCA 和 SI 结合模型中，提取了 5 个 PCs 和每个 PC 权重系数较高的 20 个 SI。对于高光谱数据，选择了 20 个 CWs 和 26 个有效 PCs。在 14 个数据集中，DS2、DS3、DS4、DS10 和 DS11 这五个数据集提供的模型输入变量在支持向量机（SVM）和最小二乘支持向量机（LS-SVM）分类器中均优于全波长（DS1）。使用这五个数据集开发的模型在 SVM 中的整体准确率范围为 91.8%至 94.5%，在 LS-SVM 中的整体准确率范围为 94.5%至 97.3%。此外，它们在 SVM 中的分类准确率提高了 0.9%至 3.6%，在 LS-SVM 中的分类准确率提高了 0.9%至 3.7%。
