应用数字图像技术诊断苎麻氮素营养的研究简报

摘要

为了实现苎麻氮素营养快速诊断,通过盆栽培养3个施氮水平的苎麻,使用信息技术和常规方法,分别获取了不同生育时期两个苎麻品种叶片的图像和氮营养元素含量.通过自主开发的苎麻叶片数字图像处理系统软件对叶片图像进行处理,并提取颜色特征值,分析叶片颜色特征值与叶片全氮营养含量之间的关系.结果表明,大部分颜色特征都与叶片全氮含量呈极显著相关.根据筛选的能有效预测苎麻叶片全氮营养的颜色特征,建立预测苎麻叶片全氮含量的6个模型,预测精度在75.95%～91.50%之间.说明应用数字图像技术诊断苎麻氮素营养是可行的.%For achieving the rapid diagnosis of ramie (Boehmeria nivea L.Gaud) nitrogen content, three nitrogen levels of ramie were planted in pots, and the standard images and the nitrogen content of ramie leaves were obtained respectively by using the information technique and the conventional method at different growth stages.Leaf images were processed by ramie leaf digital image processing software, and color features of leaf images were extracted.The relationship between color features and nitrogen contents were analyzed.The results show that most of the extracted color features are significantly correlated with total nitrogen contents of ramie leaves.Six regression models are built by using the selected color features to predict the total nitrogen contents of ramie leaves at each growth stage, and the average prediction accuracies are from 75.95％ to 91.50％.Therefore, digital image processing technology can be used to diagnose total nitrogen status of ramie.