Gu Yeong Hyeon, Yin Helin, Jin Dong, Park Jong-Han, Yoo Seong Joon
Department of Computer Science and Engineering, Sejong University, Seoul, South Korea.
Horticultural and Herbal Crop Environment Division, National Institute of Horticultural and Herbal Science, Rural Development Administration, Wanju, South Korea.
Front Plant Sci. 2021 Dec 16;12:724487. doi: 10.3389/fpls.2021.724487. eCollection 2021.
Past studies of plant disease and pest recognition used classification methods that presented a singular recognition result to the user. Unfortunately, incorrect recognition results may be output, which may lead to further crop damage. To address this issue, there is a need for a system that suggest several candidate results and allow the user to make the final decision. In this study, we propose a method for diagnosing plant diseases and identifying pests using deep features based on transfer learning. To extract deep features, we employ pre-trained VGG and ResNet 50 architectures based on the ImageNet dataset, and output disease and pest images similar to a query image a -nearest-neighbor algorithm. In this study, we use a total of 23,868 images of 19 types of hot-pepper diseases and pests, for which, the proposed model achieves accuracies of 96.02 and 99.61%, respectively. We also measure the effects of fine-tuning and distance metrics. The results show that the use of fine-tuning-based deep features increases accuracy by approximately 0.7-7.38%, and the Bray-Curtis distance achieves an accuracy of approximately 0.65-1.51% higher than the Euclidean distance.
过去对植物病虫害识别的研究使用的分类方法向用户呈现单一的识别结果。不幸的是，可能会输出错误的识别结果，这可能会导致作物进一步受损。为了解决这个问题，需要一个能够给出多个候选结果并让用户做出最终决定的系统。在本研究中，我们提出了一种基于迁移学习使用深度特征诊断植物病害和识别害虫的方法。为了提取深度特征，我们采用基于ImageNet数据集预训练的VGG和ResNet 50架构，并使用最近邻算法输出与查询图像相似的病虫害图像。在本研究中，我们总共使用了19种辣椒病虫害的23868张图像，所提出的模型在这些图像上的准确率分别达到了96.02%和99.61%。我们还测量了微调以及距离度量的效果。结果表明，使用基于微调的深度特征可将准确率提高约0.7 - 7.38%，并且布雷 - 柯蒂斯距离比欧几里得距离的准确率高出约0.65 - 1.51%。
