Bi Luning, Hu Guiping
Department of Industrial and Manufacturing Systems Engineering, Iowa State University, Ames, IA, United States.
Front Plant Sci. 2020 Dec 4;11:583438. doi: 10.3389/fpls.2020.583438. eCollection 2020.
Traditionally, plant disease recognition has mainly been done visually by human. It is often biased, time-consuming, and laborious. Machine learning methods based on plant leave images have been proposed to improve the disease recognition process. Convolutional neural networks (CNNs) have been adopted and proven to be very effective. Despite the good classification accuracy achieved by CNNs, the issue of limited training data remains. In most cases, the training dataset is often small due to significant effort in data collection and annotation. In this case, CNN methods tend to have the overfitting problem. In this paper, Wasserstein generative adversarial network with gradient penalty (WGAN-GP) is combined with label smoothing regularization (LSR) to improve the prediction accuracy and address the overfitting problem under limited training data. Experiments show that the proposed WGAN-GP enhanced classification method can improve the overall classification accuracy of plant diseases by 24.4% as compared to 20.2% using classic data augmentation and 22% using synthetic samples without LSR.
传统上，植物病害识别主要依靠人工肉眼进行。这往往存在偏差、耗时且费力。基于植物叶片图像的机器学习方法已被提出以改进病害识别过程。卷积神经网络（CNN）已被采用并证明非常有效。尽管CNN取得了良好的分类准确率，但训练数据有限的问题仍然存在。在大多数情况下，由于数据收集和标注工作艰巨，训练数据集往往较小。在这种情况下，CNN方法往往会出现过拟合问题。本文将带梯度惩罚的瓦瑟斯坦生成对抗网络（WGAN-GP）与标签平滑正则化（LSR）相结合，以提高预测准确率并解决有限训练数据下的过拟合问题。实验表明，与使用经典数据增强方法时的20.2%以及不使用LSR的合成样本时的22%相比，所提出的WGAN-GP增强分类方法可将植物病害的整体分类准确率提高24.4%。
