基于叶绿素荧光图像的辣椒叶片氮含量的预测  

Detection of pepper leaves nitrogen content in greenhouse based on chlorophyll fluorescence image

作　　者：杨一璐[1] 汪小旵[1] 李成光[1] 赵博[1] 白如月[1] YANG Yilu;WANG Xiaochan;LI Chengguang;ZHAO Bo;BAI Ruyue(College of Engineering,Nanjing Agricultural University, Nanjing 210031,China)

机构地区：[1]南京农业大学工学院,江苏南京210031

出　　处：《湖南农业大学学报（自然科学版）》2017年第1期108-111,共4页Journal of Hunan Agricultural University(Natural Sciences)

基　　金：国家自然科学基金项目(61273227);江苏省青年基金项目(BK20150686);江苏省科学技术厅项目(BN2013051)

摘　　要：提取辣椒叶片的25个叶绿素荧光图像的特征参数,其中18个特征参数与氮含量呈极显著相关(P<0.01)。用主成分分析法(PCA)提取主要特征参数,将其结果作为遗传算法优化的反向传播人工神经网络(BPNN)、广义回归神经网络(GRNN)和多元线性回归(MLR)模型的输入变量,分别建立辣椒叶片氮含量的预测模型,建模集的相关系数分别为0.959 2、0.963 3、0.943 5,预测集的相关系数分别为0.914 5、0.821 3、0.774 1。25feature parameters were extracted from chlorophyll fluorescence image of pepper leaf,including18parameterswhich was significantly correlated with the nitrogen content at the0.01level.Principal component analysis(PCA)was usedto extract the main parameters as input variables of genetic algorithm to optimize back–propagation artificial neural network(BPNN),generalized regression neural network(GRNN)and multiple linear regression(MLR),to establish the forecastmodel of hot pepper leaf nitrogen content,respectively.The correlation coefficient of three model set were0.9592,0.9633,0.9435,and correlation coefficient of prediction set were0.9145,0.8213,0.7741,respectively.

关 键 词：辣椒叶片 氮含量 叶绿素荧光图像 数字图像处理技术 

分 类 号：TP274.5[自动化与计算机技术—检测技术与自动化装置]