基于近红外光谱的商品玉米品种快速鉴别方法

现有的玉米种子品种鉴别方法检测时间长,费用高,不易大批量快速鉴别。提出了一种基于近红外光谱数据快速鉴别商品玉米品种的新方法。先使用傅里叶变换近红外光谱仪获得从4000到12000cm-1波段范围的37个商品玉米品种籽粒的漫反射光谱数据。对原始光谱进行矢量归一化预处理以消除噪声干扰,为了找到玉米品种籽粒的光谱特征波段,提出一种基于标准差的方法,进而对寻找到的玉米籽粒特征波段光谱做主成分分析(PCA),取能反映玉米品种99.98%光谱信息的前10个主成分。最后使用仿生模式识别(BPR)方法建立了37个玉米品种鉴别模型,对于每个品种的25个样本,随机挑选15个样本作为训练样本,其余10个样本作为第一测试集,其他品种共900个样本作为第二测试集。该鉴别模型对于37个玉米品种的平均正确识别率为94.3%。该方法的进一步研究有利于建立以近红外光谱为基础的物理指纹品种鉴别技术。

Fast Discrimination of Commerical Corn Varieties Based on Near Infrared Spectra

The existing methods for the discrimination of varieties of commodity corn seed are unable to process hatch data and speed up identification,and very time consuming and costly.The present paper developed a new approach to the fast discrimination of varieties of commodity corn by means of near infrared spectral data.Firstly,the experiment obtained spectral data of 37 varieties of commodity corn seed with the Fourier transform mear infrared spectrometer in the wavenumber range from 4 000 to 12 000 cm-1.Secondly,the original data were pretreated using statistics method of normalization in order to eliminate noise and improve the efficiency of models.Thirdly,a new way based on sample standard deviation was used to select the characteristic spectral regions,and it can search very different wavenumhers among all wavenumbers and reduce the amount of data in part.Fourthly,principal component analysis(PCA) was used to compress spectral data into several variables,and the cumulate reliabilities of the first ten components were more than 99.98%.Finally,according to the first ten components,recognition models werc cstablished based on BPR For every 25 samples in each variety,15 samples were randomly selected as the training set.The remaining 10 samples of the same variety were used as the first testing set,and all the 900.samples of the other varieties were used as the second testing set.Calculation results showed that the average correctness recognition rate of the 37 varieties of corn seed was 94.3%.Testing results indicate that the discrimination method had higher precision than the discrimination of various kinds of commodity corn seed.In short,it is feasible to discriminate various varieties of commodity corn seed based on near infrared spectroscopy and BPR.