Zhou Huiru, Deng Jie, Cai Dingzhou, Lv Xuan, Wu Bo Ming
College of Plant Protection, China Agricultural University, Beijing, China.
Front Plant Sci. 2022 Jul 5;13:910878. doi: 10.3389/fpls.2022.910878. eCollection 2022.
In recent years, the convolution neural network has been the most widely used deep learning algorithm in the field of plant disease diagnosis and has performed well in classification. However, in practice, there are still some specific issues that have not been paid adequate attention to. For instance, the same pathogen may cause similar or different symptoms when infecting plant leaves, while the same pathogen may cause similar or disparate symptoms on different parts of the plant. Therefore, questions come up naturally: should the images showing different symptoms of the same disease be in one class or two separate classes in the image database? Also, how will the different classification methods affect the results of image recognition? In this study, taking rice leaf blast and neck blast caused by , and rice sheath blight caused by as examples, three experiments were designed to explore how database configuration affects recognition accuracy in recognizing different symptoms of the same disease on the same plant part, similar symptoms of the same disease on different parts, and different symptoms on different parts. The results suggested that when the symptoms of the same disease were the same or similar, no matter whether they were on the same plant part or not, training combined classes of these images can get better performance than training them separately. When the difference between symptoms was obvious, the classification was relatively easy, and both separate training and combined training could achieve relatively high recognition accuracy. The results also, to a certain extent, indicated that the greater the number of images in the training data set, the higher the average classification accuracy.
近年来，卷积神经网络一直是植物病害诊断领域应用最广泛的深度学习算法，并且在分类方面表现出色。然而，在实际应用中，仍存在一些未得到充分关注的具体问题。例如，同一病原体在感染植物叶片时可能会导致相似或不同的症状，而同一病原体在植物的不同部位可能会引起相似或不同的症状。因此，自然而然会出现这样的问题：在图像数据库中，显示同一种病害不同症状的图像应该归为一类还是分为两类？此外，不同的分类方法会如何影响图像识别的结果？在本研究中，以由……引起的水稻叶瘟和穗颈瘟以及由……引起的水稻纹枯病为例，设计了三个实验，以探讨数据库配置如何影响在识别同一植物部位上同一种病害的不同症状、不同部位上同一种病害的相似症状以及不同部位上的不同症状时的识别准确率。结果表明，当同一种病害的症状相同或相似时，无论它们是否在同一植物部位，对这些图像的类别进行组合训练比单独训练能获得更好的性能。当症状差异明显时，分类相对容易，单独训练和组合训练都能达到较高的识别准确率。结果还在一定程度上表明，训练数据集中的图像数量越多，平均分类准确率越高。
