基于ResNet-50深度卷积网络的果树病害智能诊断模型研究

目的/意义]果树病害危及农业生产安全,运用人工智能技术帮助果农及时准确地识别果树病害对保障农业安全生产具有重要意义。方法/过程]采用10000张果树叶片病斑图像数据集,通过旋转、污化、增噪、切割等图像增强手段,提高样本图像的多样性;使用ResNet-50深度卷积网络模型,进行机器学习,获得果树病害识别模型,并基于此模型开发了应用软件提供在线诊断服务。结果/结论]实验结果表明:该模型对4种果树病害的平均识别率达到92.9%,和相关研究成果相比具有较好的诊断效果。

The Intelligent Diagnosis Model of Fruit Tree Disease Based on ResNet-50

Purpose/Significance]Fruit tree diseases endanger the safety of agricultural production,and the use of artificial intelligence technologies to help fruit growers identify fruit tree diseases in a timely and accurate manner is of great significance to ensure safe agricultural production.Method/Process]Using 10000 fruit tree leaf diseased spots image data sets,through image enhancement methods such as rotation,pollution,noise enhancement,and cutting to improve the diversity of sample images;using the ResNet-50 deep convolutional network model to perform machine learning to obtain the fruit tree diseases identification model,and develop application software based on this model to provide online diagnostic services.Results/Conclusions]The experimental results show that the average recognition rate of the four fruit tree diseases reached 92.9%,which has a better diagnostic effect compared with related research results.